Article

Exposing digital video forgery by ghost shadow artifact

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

In the digital multimedia era, it is increasingly important to ensure the integrity and authenticity of the vast volumes of video data. A novel approach is proposed for detecting video forgery based on ghost shadow artifact in this paper. Ghost shadow artifact is usually introduced when moving objects are removed by video inpainting. In our approach, ghost shadow artifact is accurately detected by inconsistencies of the moving foreground segmented from the video frames and the moving track obtained from the accumulative frame differences, thus video forgery is exposed. Experiments show that our approach achieves promising results in video forgery detection.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Aside from pixel-similarity and correlation, object and motion features are also useful for the detection of copy-paste forgeries. In Ref. [25], ghost artifacts, which arise when moving objects are removed from video frames, were used to detect forgeries. A novel concept was presented in Ref. [26], where tampered videos were detected by identifying physically improbable trajectories of solid objects in the video. ...
... Contrary to the correlation-based schemes, motion and object feature based techniques were found to be much more resilient to compression artifacts. The technique proposed in Ref. [25] could effectively handle MPEG-2 encoded videos but was relatively less effective in case of H.264/AVC videos. The forgery localization process of this technique was found to be imprecise as well. ...
... The methods suggested in Refs. [25,27] worked for videos with static backgrounds only. Moreover the technique in Ref. [27] was unfit for videos with very little object motion. ...
Article
Amidst the continual march of technology, we find ourselves relying on digital videos to proffer visual evidence in several highly sensitive areas such as journalism, politics, civil and criminal litigation, and military and intelligence operations. However, despite being an indispensable source of information with high evidentiary value, digital videos are also extremely vulnerable to conscious manipulations. Therefore, in a situation where dependence on video evidence is unavoidable, it becomes crucial to authenticate the contents of this evidence before accepting them as an accurate depiction of reality. Digital videos can suffer from several kinds of manipulations, but perhaps, one of the most consequential forgeries is copy-paste forgery, which involves insertion/removal of objects into/from video frames. Copy-paste forgeries alter the information presented by the video scene, which has a direct effect on our basic understanding of what that scene represents, and so, from a forensic standpoint, the challenge of detecting such forgeries is especially significant. In this paper, we propose a sensor pattern noise based copy-paste detection scheme, which is an improved and forensically stronger version of an existing noise-residue based technique. We also study a demosaicing artifact based image forensic scheme to estimate the extent of its viability in the domain of video forensics. Furthermore, we suggest a simplistic clustering technique for the detection of copy-paste forgeries, and determine if it possess the capabilities desired of a viable and efficacious video forensic scheme. Finally, we validate these schemes on a set of realistically tampered MJPEG, MPEG-2, MPEG-4, and H.264/AVC encoded videos in a diverse experimental set-up by varying the strength of post-production re-compressions and transcodings, bitrates, and sizes of the tampered regions. Such an experimental set-up is representative of a neutral testing platform and simulates a real-world forgery scenario where the forensic investigator has no control over any of the variable parameters of the tampering process. When tested in such an experimental set-up, the four forensic schemes achieved varying levels of detection accuracies and exhibited different scopes of applicabilities. For videos compressed using QFs in the range 70-100, the existing noise residue based technique generated average detection accuracy in the range 64.5%-82.0%, while the proposed sensor pattern noise based scheme generated average accuracy in the range 89.9%-98.7%. For the aforementioned range of QFs, average accuracy rates achieved by the suggested clustering technique and the demosaicing artifact based approach were in the range 79.1%-90.1% and 83.2%-93.3%, respectively.
... Aside from pixel/noise correlations, the presence of a copy-paste forgery can also be revealed by focusing on the detection of those artifacts that occur when an object or region is removed from a frame, or when an object is added to it. For instance, ghost shadow artifacts, which arise when moving objects are removed from video frames, were used as forensic features in [14]. In [15], copy-paste forgeries were detected by identifying physically improbable trajectories of any solid objects in the video. ...
... They do, however, have their own unique set of drawbacks. For instance, while the technique proposed [14] could effectively handle MPEG-2 encoded videos, it was relatively less effective in case of H.264/AVC videos. The forgery localization process of this technique was found to be imprecise as well. ...
... The forgery localization process of this technique was found to be imprecise as well. The methods suggested in [14,16,17] worked for videos with static backgrounds only. Furthermore, while the technique presented in [16] was unfit for videos with very little object motion, those suggested in [17,23] were ineffective in cases where fast-moving objects were removed from the scene, or when the removed objects were small in size, or when the video exhibited complex background scenes. ...
Article
Full-text available
Digital videos are an incredibly important source of information, and as evidence, they are highly inculpatory. Digital videos are also inherently prone to conscious semantic manipulations, such as copy–paste forgeries, which involve insertion or removal of objects into or from a set of frames. Such forgeries involve direct manipulation of the information presented by a video scene, thus having an immediate effect on the meaning conveyed by that scene. Given the highly influential nature of video data and the fact that they are easy to manipulate, it becomes important to devise measures that can help ascertain their integrity and authenticity, so that we can be certain of their ability to serve as reliable evidence. The challenge of detecting copy–paste forgeries in digital videos has been at the receiving end of much innovation over the last decade, and as a result, the available literature in this domain has grown to considerable proportions. However, thorough analysis of this literature appears to show that the task of detecting such forgeries necessitates the use of elaborate and operationally restrictive procedures, and somehow cannot be accomplished via a relatively simpler process, whose method of operation imposes little to no restrictions on its scope of applicability. With the aim of quashing this notion, in this paper, we present two simple forensic solutions that can enable an analyst to detect copy–paste forgeries quickly and effectively, without having to resort to any complicated analyses or relying on unrealistic presumptions. These solutions are based on optical flow inconsistency analysis and pattern noise abnormality analysis, and have been validated on a substantial set of realistically tampered test videos in a diverse experimental set-up, which is representative of a neutral testing platform and simulates a real-world heterogeneous forensic environment, where the analyst has no control over any of the variable parameters of the video creation or manipulation process. When tested in such an experimental set-up, the proposed solutions achieved an average accuracy rate of 98% and demonstrated attributes desired of an efficacious and practical forensic solution, all the while validating our initial hypothesis that not only can the task of copy–paste detection be accomplished in a fast and uncomplicated manner, but also that in an actual forgery scenario, the less onerous a forensic solution is, the more likely it is to succeed.
... Moreover, most passive techniques are based on the video characteristics and tampering artefacts. An example of such characteristics and artefacts includes noise residue characteristics [27], readout noise characteristics [28], sensor pattern noise, variation in noise level functions [29], ghost shadow artefacts [30], and lightening and compression artefacts [31]. ...
... The use of Ghost Shadow Artefacts(GSA) was proposed in order to detect video inpainting forgery associated with moving objects in [30]. GSA are unnatural flicker like structures that are observed in a video resulting from the discontinuity across an inpainted region [37]. ...
... The performance of the proposed technique is compared with techniques proposed in [27], [30] and [43]. These selected techniques are considered because of their popularity and average performance rate of 96.61, 93.40 and 97.52 respectively for video inpainting forgery detection over the years. ...
Article
Full-text available
The use of digital video during forensic investigation helps in providing evidence related to crime scene. However, due to freely available user friendly video editing tools, the forgery of acquired digital videos that are used as evidence in a law suit is now simpler and faster. As a result, it has become easier for manipulators to alter the contents of digital evidence. For instance, inpainting technique is used to remove an object from a video without leaving any artefact of illegal tampering. Therefore, this paper presents a technique for detecting and locating inpainting forgery in a video sequence with static camera motion. Our technique exploits statistical correlation of Hessian matrix (SCHM) to detect and locate tampered regions within a video sequence. The results of our experiments prove that the technique effectively detect and locate areas which are tampered using both texture and structure based inpainting with an average precision rate of 99.79% and an average false positive rate of 0.29%.
... In [23], this scheme is effective but not suitable for large videos due to large computation time [21]. In [5,8,39], the techniques have worked only in static background videos. In [30,31], the methods do not work while duplication is done within moving camera and static background videos. ...
... These become ineffective if duplication is made in moving camera or static background video [20]. In [39], the authors have described a method in which ghost shadow artifact used as a feature for the detection of region duplication. In [5,8], the authors have provided an algorithm based on noise and quantization residue in order to detect the region duplication. ...
... In [5,8], the authors have provided an algorithm based on noise and quantization residue in order to detect the region duplication. But the algorithms [5,8,39] are worked only in static background videos only [20]. In [40], this aims at improving BoW-based image retrieval via indexing-level feature fusion. ...
Article
Full-text available
In this paper, we present a passive blind scheme consisting of two different algorithms to detect frame and region duplication forgeries in videos. We have examined the video frame duplication forgery in three different forms such as duplication of a sequence of consecutive video frames at long continue running position, duplication of many such sequences having different lengths at many different locations and duplication from other videos having different and same dimensions which can raise a serious problem in the real world scenario. The algorithm I of proposed scheme has detected these three different forms of copy-moved frame duplication forgery in videos by obtaining the mean features of each video frame for evaluating the correlation between sequences. In this paper, we have also analysed forged regular and irregular region within same frame at different locations and from other frame to one or more sequences of consecutive frames of the same video at same locations. It creates a challenge to detect this copy-move forgery due to slightly change in pixel intensity values in the duplicated region and providing high correlation as authentic region. The algorithm II of proposed scheme has detected these copy-moved region duplication forgeries in videos by locating the position of error with threshold process in order to calculate the similarities between regions of two frames or within affected frame. In this paper, the experimental results show the higher detection accuracy and execution time efficiency of proposed scheme than the latest algorithms with satisfactory performance.
... Existing works usually exploit phenomena connected to motion in order to detect editing. So far, two approaches have been proposed: (i) the one in [73], based on artifacts introduced by video inpainting, (ii) the one in [74], that reveals inconsistencies in the motion of objects in free-flight. ...
... Going into details, Zhang et al. [73] propose a method to detect video inpainting, which is a technique that automatically replaces some missing content in a frame by reproducing surrounding textures. Although originally developed for still images, this technique is also applicable frameby-frame to video signals introducing annoying artifacts, known as "ghost shadows", due to temporal discontinuity of the inpainted area. ...
Conference Paper
Full-text available
Validating a given multimedia content is nowadays quite a hard task because of the huge amount of possible alterations that could have been operated on it. In order to face this problem, image and video experts have proposed a wide set of solutions to reconstruct the processing history of a given multimedia signal. These strategies rely on the fact that non-reversible operations applied to a signal leave some traces ("footprints") that can be identified and classified in order to reconstruct the possible alterations that have been operated on the original source. These solutions permit also to identify which source generated a specific image or video content given some device-related peculiarities. The paper aims at providing an overview of the existing video processing techniques, considering all the possible alterations that can be operated on a single signal and also the possibility of identifying the traces that could reveal important information about its origin and use.
... Object removal video forgery is achieved by using inpainting algorithms [33]- [35]. The following works are proposed to detect object removal video forgery [36]- [44]. Zhang et al. developed an approach that uses ghost shadow artifact to identify inconsistencies between foreground mosaic and trajectory of moving foreground [36]. ...
... The following works are proposed to detect object removal video forgery [36]- [44]. Zhang et al. developed an approach that uses ghost shadow artifact to identify inconsistencies between foreground mosaic and trajectory of moving foreground [36]. Hsu et al. introduced an approach that uses temporal correlation of noise residues to identify irregular changes in the correlation of noise residues throughout video frames [37]. ...
Article
Full-text available
In recent years, video surveillance has become essential for security applications used to monitor many organizations and locations, and it is therefore important to ensure the reliability of these surveillance videos. Unfortunately, surveillance videos can be forged with little effort by deleting an object from a video scene while leaving no visible traces. A fundamental challenge in video security is to determine whether or not an object has been removed from a video. This task is particularly challenging due to the lack of ground truth bases that can be used to verify the originality and integrity of video contents. In this paper, we propose a novel approach based on sequential and patch analyses to detect object removal forgery and to localize forged regions in videos. Sequential analysis is performed by modeling video sequences as stochastic processes, where changes in the parameters of these processes are used to detect a video forgery. Patch analysis is performed by modeling video sequences as a mixture model of normal and anomalous patches, with the aim to separate these patches by identifying the distribution of each patch. We localize forged regions by visualizing the movement of removed objects using anomalous patches. We conduct our experiments at both pixel and video levels to determine the effectiveness and efficiency of our approach to detection of video forgery. The experimental results show that our approach achieves excellent detection performance with low-computational complexity and leads to robust results for compressed and low-resolution videos.
... Furthermore, Figure 4 presents studies [13,15,[55][56][57][58] ...
... An approach which uses ghost shadow artifact is accurately detected by inconsistencies of the moving foreground segmented from the video frames and the moving track obtained [57]. ...
Article
Full-text available
In the current times the level of video forgery has increased on the internet with the increase in the role of malware that has made it possible for any user to upload, download and share objects online including audio, images, and video. Specifically, Video Editor and Adobe Photoshop are some of the multimedia software and tools that are used to edit or tamper medial files. Added to this, manipulation of video sequence in a way that objects within the frame are inserted or deleted are among the common malicious video forgery operations. In the present study, literature concerning video forgery is reviewed primarily those that use several video forgery detection in the form of passive blind method on three types of forgery namely cloning forgery, source cameral identification and splice forgery. The present study employed a video authentication method that detects and determines both region duplication and frame duplication in terms of video forgery, and locates factors that impact video forgery. In the present study, video processing into sub-blocks and the moments geometric features for every macro-block were extracted. This led to the enhanced accuracy of detection. Moreover, the optimum sorting algorithm led to minimized computational time taking account number of blocks and features numbers into consideration.
... intra-frame and inter-frame forgery), e.g. [7][8][9][10][11][12][13][14][15][16]. ...
... In their method, a given video is split into subparts, and different kinds of correlation coefficients are computed to exploit the similarity. Zhang et al. [14] proposed to expose ghost shadows in accumulative difference image (ADI) to detect video inpainting. Conotter et al. [15] focused on the detection of physically implausible trajectories of objects in free-flight. ...
Conference Paper
Full-text available
With the extensive equipment of surveillance systems, the assessment of the integrity of surveillance videos is of vital importance. In this paper, an algorithm based on optical flow and anomaly detection is proposed to authenticate digital videos and further identify the inter-frame forgery process (i.e. frame deletion, insertion, and duplication). This method relies on the fact that forgery operation will introduce discontinuity points to the optical flow variation sequence and these points show different characteristics depending on the type of forgery. The anomaly detection scheme is adopted to distinguish the discontinuity points. Experiments were performed on several real-world surveillance videos delicately forged by volunteers. The results show that the proposed algorithm is effective to identify forgery process with localization, and is robust to some degree of MPEG compression.
... The work in [94] was a novel technique that could identify a forged video by detecting ghost shadow artifacts, which arise when moving objects are removed from video frames. The video was first segmented into static background and moving foreground via bock matching. ...
... We analyzed the performances of the following copy-paste detection techniques: the noise-based approaches proposed in [38,82], the noise and quantization residue-based scheme of [84], motion-residue-based approach proposed in [86], the pixel-coherence analysis technique 2 suggested in [87], the object-based technique suggested in [94], and the optical-flow-based method proposed in [98]. Table 2 presents a comparative summary of the outcomes, as a function of various compression quality factors (QF) and bitrates. ...
Article
Full-text available
In this digital day and age, we are becoming increasingly dependent on multimedia content, especially digital images and videos, to provide a reliable proof of occurrence of events. However, the availability of several sophisticated yet easy-to-use content editing software has led to great concern regarding the trustworthiness of such content. Consequently, over the past few years, visual media forensics has emerged as an indispensable research field, which basically deals with development of tools and techniques that help determine whether or not the digital content under consideration is authentic, i.e., an actual, unaltered representation of reality. Over the last two decades, this research field has demonstrated tremendous growth and innovation. This paper presents a comprehensive and scrutinizing bibliography addressing the published literature in the field of passive-blind video content authentication, with primary focus on forgery/tamper detection, video re-capture and phylogeny detection, and video anti-forensics and counter anti-forensics. Moreover, the paper intimately analyzes the research gaps found in the literature, provides worthy insight into the areas, where the contemporary research is lacking, and suggests certain courses of action that could assist developers and future researchers explore new avenues in the domain of video forensics. Our objective is to provide an overview suitable for both the researchers and practitioners already working in the field of digital video forensics, and for those researchers and general enthusiasts who are new to this field and are not yet completely equipped to assimilate the detailed and complicated technical aspects of video forensics.
... For detection considering geometry or physical lighting properties of a crimes scene, it is very difficult to justify as whether such a scene is consistent or not. Several algorithms have been developed over the years considering this method including [22], which considers "ghost shadows" and [16] who are concerned with three-dimensional parabolic trajectory with considering of objects in a video. The above mentioned methods are useful in handling particular tasks. ...
... To deal with this attacker we can leverage image and video forensics tools [8,17,23,48]. For example, video forensics can help us detect non-sequential frames, e.g., inconsistency in the lighting of sequential frames, discrepancy between objects' locations, or non-uniformity between resolution of the images. ...
Conference Paper
Full-text available
We propose a new way to verify the integrity and freshness of footage from security cameras by sending visual challenges to the area being monitored by the camera. We study the effectiveness of periodically updating plain text and QR code visual challenges, propose attack detection statistics for each of them, and study their performance under normal conditions (without attack) and against a variety of adversaries. Our implementation results show that visual challenges are an effective method to add defense-in-depth mechanisms to improve the trustworthiness of security cameras.
... The limitation of this work is its lack of ability to deal with videos recorded from dynamic scenes. [14] proposes a system that detects forgeries in a video which involves moving objects using ghost shadow artifact that are introduced as a result of video inpainting. Video inpainting as defined by [15] and [16] is a technique that is used to complete or bring back a removed object in a video. ...
Conference Paper
Full-text available
Technological advancement of various video and image processing tools has made tempering of digital video easy and faster. This review paper focuses on passive techniques that are employed for detecting forgeries in a digital video. Passive forgery detection techniques are methods used for detecting the authenticity of a video without depending on pre-embedded information. The techniques exploit the use of statistical or mathematical properties that are distorted as a result of video tempering for forgery detection. Passive video forgery detection approach has a great prospect in multimedia security, information security and pattern recognition. In this paper, we divide passive techniques for video forensics into three categories; Statistical correlation of video features, frame-based for detecting statistical anomalies, and the inconsistency features of different digital equipment. The discussion also covers the trends, limitations and idea for improvements of passive forgery detection techniques.
... Recently, hackers have found numerous techniques to modify digital content, among these techniques are copy-moving and cloning. Video tampering can be categorized into three areas: temporal domain, spatial domain, and spatio-temporal domain [3,12,[16][17][18][19][20]. Tampering with videos spatially (spatial tampering) is possible by forgers as pixels inside a video frame or neighbouring video frames are manipulated by them. ...
... In [11], an algorithm is proposed to detect forged regions in a video based on the inconsistencies of noise characteristics, which occurred due to the forged areas patched from different videos. A method based on accumulated differential image is proposed in literature [29], which uses the textural features around the tampered area to detect the tampering traces. This method could realize the detection of the moving objects to be removed in static background, but experimental results can be easily affected by the shooting scene environment, such as trees, flowers and plants, etc. ...
Article
Full-text available
Blue screen compositing is one of the most common methods to do video forgery. However, few algorithms have been proposed to detect the forgery in this form. This paper presents a 3-stage Foreground Analysis and Tracking algorithm (3FAT) to detect blue screen compositing. The 3FAT algorithm contains three major stages: foreground block extraction, forged block detection and forged block tracking. The first stage extracts the foreground blocks by a multi-pass foreground locating method. In the second stage, a feature-comparison level fusion of local features consisting of luminance and contrast is put forward to seek out the tampered foreground block. In the last stage, a fast target search algorithm based on Compressive Tracking is used to track the tampered block of subsequent frames. Compared with previous algorithm, 3FAT can not only rule out the distractions of noise and other moving foregrounds, but also be applied to any video format, bit rate and encoding mechanism. The experiments show that the 3FAT algorithm has higher accuracy and performs well in terms of speed.
... Ghost Shadow L [18] ü (GMM) (EM) [19] [20][18] [19] ...
Article
The characteristics of various video forgery operations and their influences to video passive forensics were analyzed. From two aspects of authenticity and source identifications, typical approaches in passive video forensics, such as those video forgery trails-based and video capturing device-based techniques, are summarized. The main problems exiting in current research field and some urgent topics for future research are also investigated in detail.
... Histogram of oriented gradients feature matching and video compression properties were applied to detect copy-paste detection by Subramanyam and Emmanuel [8]. Zhang et al. [9] used ghost shadow to detect copy-paste forgery. Frame insertion and deletion are two of the most common inter-frame forgeries, the detection of which is our research focus in this paper. ...
Article
Frame insertion and deletion are common inter-frame forgery in digital videos. In this paper, an efficient method based on quotients of correlation coefficients between local binary patterns (LBPs) coded frames is proposed. This method is composed of two parts: feature extraction and abnormal point detection. In the feature extraction, each frame of a video is coded by LBP. Then, quotients of correlation coefficients among sequential LBP-coded frames are calculated. In the abnormal point detection, insertion and deletion localization is achieved by using Tchebyshev inequality twice followed by abnormal points detection based on decision-thresholding. Experimental results show that our method has high detection accuracy and low computational complexity. Copyright © 2014 John Wiley & Sons, Ltd.
... The sequence of events recorded through frames is jumbled or reordered such that the correct sequence is lost and wrong information is propagated. Yuting et al. [5], Stamm et al. [6] have exploited the frame grouping strategy implemented by common video encoders to detect inter frame forgery detection. ...
Chapter
The credibility of digital videos obtained from various sources like surveillance cameras, smartphones, webcams used as evidence in courtrooms, medical world, and journalism needs to be verified for its authenticity and integrity to detect video forgery. The proposed forensic approach detects inter frame forgery due to frame duplication based on statistical correlation for the digital video. The statistical correlation in video content of the frames has been explored through textural features to identify frame duplication and is verified. Experimental results demonstrate accuracy in identifying frame replication.
... Proposed scheme attempts to detect duplicate and modified copies of a video primarily based on peculiarities of imaging sensors rather than content characteristics only. Zhang et al. [14] discuss an approach for detecting video forgery based on ghost shadow artifact. The artifact ghost shadow comes into action when object which is moving is removed by in-painting. ...
Article
Full-text available
Recent years have seen tremendous increase in crime and terrorism all over the world which has necessitated continuous surveillance of public spaces, commercial entities and residential areas. CCTV cameras are an integral part of any modern surveillance system and have evolved significantly. They are a vital part of any investigation that follows a criminal or terrorism incident by providing invaluable evidence. In this paper, we show that the Advance Systems Format (ASF) file used in most IP cameras, which is also the main file containing metadata about the streaming packets, is vulnerable to forgery. This file is stored in plain text and any technically savvy person can forge it; therefore, a mechanism is needed to prevent it. To that end, we have gathered critical artifacts from an ASF file of IP cameras and carried out their forensic analysis. The analysis performed during this study demonstrates successful detection of forgery/tampering of evidence in IP cameras.
... The first category detects inter-frame tampering including frame deletion/addition, and frame duplication [11,25,31,36]. The second category is to expose object-based video forgery [12][13][14]40], which adds new object to a video scene or removes existing object from it. The clues exploited to expose video forgeries involve optical flow consistency [11], velocity field consistency [36], Zernike moments of opponent chromaticity [25], physical inconsistencies [14], object contour irregularity [12], and motion residuals [13]. ...
Article
Full-text available
Motion compensated frame interpolation (MCFI) is a special frame based video manipulation, which increases the temporal continuity of low frame rate videos by synthesizing new frames between successive frames. MCFI might also be used to counterfeit high frame-rate videos, which mislead users’ attraction and waste storage spaces in video-sharing websites. Existing MCFI detectors are designed to judge the absence or presence of MCFI forgery in a controllable environment of known MCFI techniques. Practical detector should consider the possibility of unknown MCFI techniques. We are motivated to propose a robust MCFI detector for more practical scenarios. Considering the effects of non-motion regions in candidate frame, the statistical moments are firstly extracted from motion-aligned frame differences (MAFD). Then, the one-class support vector machine (SVM), following a training stage capturing the properties of original frames, is exploited to judge whether the candidate frame is interpolated by MCFI or not. Finally, a special interpolated frame detection (SIFD) is designed to pick out interpolated frames, which are synthesized from two consecutive reference frames with no motion vectors (MVs) or less MVs. A series of experiments evaluated on four representative MCFI techniques have shown promising results.
... Based on the temporal and spatial correlations, Wang et al. [132] have exploited the correlation coefficient as a measure to detect the forgery in the video. Based on ghost shadow artefact, Zhang et al. [148] have presented a technique to identifies the video inpainting forgeries such as TCP and ETS. The statistical properties of the object based on the Adjustable Width Object Boundary (AWOB) algorithm is used by Chen et al. [19] to identify the object insertion or removal forgery in the video. ...
Article
Full-text available
Digital videos are one of the most widespread forms of multimedia in day to day life. These are widely transferred over social networking websites such as Facebook, Instagram, WhatsApp, YouTube, etc. through the Internet. Availability of modern and easy to use editing tools have facilitated the modification of the contents of the digital videos. Therefore, it has become an essential concern for the legitimacy, trustworthiness, and authenticity of these digital videos. Digital video forgery detection aims to identify the manipulations in the video and to check its authenticity. These techniques can be divided into active and passive techniques. In this paper, a comprehensive survey on video forgery detection using passive techniques have been presented. The primary goal of this survey is to study and analyze the existing passive video forgery detection techniques. Firstly, the preliminary information required for understanding video forgery detection is presented. Later, a brief survey of existing passive video forgery detection techniques based on the features, forgery identified, datasets used, and performance parameters detail along with their limitations are reviewed. Then, anti-forensics strategy and deepfake detection in the video are discussed. After that, standard benchmark video forgery datasets and the generalized architecture for passive video forgery detection techniques are discussed. Finally, few open challenges in the field of passive video forgery detection are also described.
... They measure the inter-field and interframe motions for the interlaced video that is the same for an authentic video but may be different for a doctored video. [29] presented another strategy for the identification of video tampering by using the ghost shadow artifact that was implemented through the video inpainting procedure. In this strategic approach, researchers compute the foreground mosaic and compare it with the moving foreground track if they are consistent, then the input video is authentic without ghost shadow artifact otherwise the input video can be a forged video with ghost shadow artifact. ...
... However, the research on digital video forensics is still in its infancy. The most representative works are summarized as follows: (1) forensics by the inconsistent trails during the imaging process such as PRNU [5], noise level functions [6]; and (2) forensics by the traces of video tampering, such as ghosting shadow [7], block artefacts [8], GOP periodicity [9] and motion compensated edge artefacts (MCEA) [10]. These methods are effective to detect traditional forgery operations, including copy-paste, double MPEG compression and frame-based tampering. ...
Conference Paper
In this paper, we present a passive approach for effective detection and localization of forgery from video sequences. Our approach analyzes spatio-temporal slices from 3-D video volumes to detect and localize regions tampered by temporal copy-and-paste and texture synthesis. Experiment shows that the proposed approach outperforms previous approaches, and can effectively detect and localize tampered regions.
Article
Inter-frame forgery is the most common type of video forgery methods. However, few algorithms have been suggested for detecting this type of forgery, and the former detection methods cannot ensure the detection speed and accuracy at the same time. In this paper, we put forward a novel video forgery detection algorithm for detecting an inter-frame forgery based on Zernike opponent chromaticity moments and a coarseness feature analysis by matching from the coarse-to-fine models. Coarse detection applied to extract abnormal points is carried out first; each frame is converted from a 3D RGB color space into a 2D opposite chromaticity space combined with the Zernike moment correlation. The juggled points are then obtained exactly from abnormal points using a Tamura coarse feature analysis for fine detection. Coarse detection not only has a high-efficiency detection speed, but also a low omission ratio; however, it is accompanied by mistaken identifications, and the precision is not ideal. Therefore, fine detection was proposed to help to make up the difference in precision. The experimental results prove that this algorithm has a higher efficiency and accuracy than previous algorithms.
Article
Passive multimedia forensics has become an active topic in recent years. However, less attention has been paid on video forensics. The research on video forensics, and especially on automatic detection of object-based video forgery is still in its infancy. In this paper, we develop an approach for automatic identification and forged segment localization of object-based forged video encoded with advanced frameworks. The proposed approach starts with a frame manipulation detector. An auto- matic algorithm is proposed to identify object-based video forgery based on the frame manipulation detector. Then a two-stage automatic algorithm is provided to accurately locate the forged video segments in the suspicious video. In order to construct the proposed frame manipulation detector, motion residuals are generated from the target video frame sequence. We regard the object-based forgery in video frames as image tampering in the motion residuals, and employ the feature extractors which are originally built for still image steganalysis to extract forensic features from the motion residuals. The experiments show that the proposed approach achieves excellent results in both forged video identification and automatic forged temporal segment localization.
Conference Paper
In this paper we present a novel blind video forgery detection method by applying Markov models to motion in videos. Motion is an important aspect of video forgery detection as it effects forgery detection in videos. Most of the current video forgery detection algorithms do not consider motion in their approach. Motion is usually captured from motion vectors and prediction error frame. However capturing motion for I-frame is computationally expensive, so in this paper we extract the motion information by applying collusion on successive frames. First a base frame is obtained by applying collusion on successive frames and the difference between actual and estimate gives information about motion. Then we apply Markov models on this motion residue and apply pattern recognition on this. We used Support Vector Machines (SVMs) in our experiment. We obtained an accuracy of 87% even for reduced feature set.
Article
In this paper, we present a passive approach for effective detection and localization of region-level forgery from video sequences possibly with camera motion. As most digital image/video capture devices do not have modules for embedding watermark or signature, passive forgery detection which aims to detect the traces of tampering without embedded information has become the major focus of recent research. However, most of current passive approaches either work only for frame-level detection and cannot localize region-level forgery, or suffer from high false detection rates for localization of tampered regions. In this paper, we investigate two common region-level inpainting methods for object removal, temporal copy-and-paste and exemplar-based texture synthesis, and propose a new approach based on spatio-temporal coherence analysis for detection and localization of tampered regions. Our approach can handle camera motion and multiple object removal. Experiments show that our approach outperforms previous approaches, and can effectively detect and localize regions tampered by temporal copy-and-paste and texture synthesis.
Article
For digital video, object-based manipulations, such as adding, removing or changing objects, are usually malicious tamper/forgery operations. Compared with the conventional double compression or framebased operation, it makes more sense to detect these object-based manipulations because they might directly affect video content. This paper concentrates on video object contour and its Adjustable Width Object Boundary (AW OB), digs the trace of forgery in small-scale by analysing detail coefficients of Non-Subsampled Contourlet (NSCT) and gradient information, of which feature vectors are obtained and combined as the input of Support Vector Machine (SVM), thus natural objects and forged ones will be successfully classified. The proposed algorithm turns out to be effective with a high accuracy of correct detection up to 95%.
Article
Bit rate is one of the important criterions for digital video quality. With some video tools, however, video bit rate can be easily increased without improving the video quality at all. In such a case, a claimed high bit rate video would actually have poor visual quality if it is up-converted from an original lower bit rate version. Therefore, exposing fake bit rate videos becomes an important issue for digital video forensics. To the best of our knowledge, although some methods have been proposed for exposing fake bit rate MPEG-2 videos, no relative work has been reported to further estimate their original bit rates. In this paper, we first analyze the statistical artifacts of these fake bit rate videos, including the requantization artifacts based on the first-digit law in the DCT frequency domain (12-D) and the changes of the structural similarity indexes between the query video and its sequential bit rate down-converted versions in the spatial domain (4-D), and then we propose a compact yet very effective 16-D feature vector for exposing fake bit rate videos and further estimating their original bit rates. The extensive experiments evaluated on hundreds of video sequences with four different resolutions and two typical compression schemes (i.e., MPEG-2 and H.264/AVC) have shown the effectiveness of the proposed method compared with the existing relative ones.
Article
Video processing software is often used to delete moving objects and modify the forged regions with the information provided by the areas around them. However, few algorithms have been suggested for detecting this form of tampering. In this paper, a novel algorithm based on compressive sensing is proposed for the detection in which the moving foreground was removed from background. Firstly, the features of the difference between frames are obtained through K-SVD (k-Singular Value Decomposition), and then random projection is used to project the features into the lower-dimensional subspace which is clustered by k-means, and finally the detection results are combined to output. The experimental results show that our algorithm has higher detection accuracy and better robustness than that of the previous algorithms.
Article
Image completion techniques aim to complete selected regions of an image in a natural looking manner with little or no user interaction. Video Completion, the space–time equivalent of the image completion problem, inherits and extends both the difficulties and the solutions of the original 2D problem, but also imposes new ones—mainly temporal coherency and space complexity (videos contain significantly more information than images). Data-driven approaches to completion have been established as a favoured choice, especially when large regions have to be filled. In this survey, we present the current state of the art in data-driven video completion techniques. For unacquainted researchers, we aim to provide a broad yet easy to follow introduction to the subject (including an extensive review of the image completion foundations) and early guidance to the challenges ahead. For a versed reader, we offer a comprehensive review of the contemporary techniques, sectioned out by their approaches to key aspects of the problem.
Conference Paper
In the context of triple play the media business is exploding. Incidents that TV shows and Web videos are tampered maliciously occur occasionally. To solve this problem, a LOF-Co-Forest algorithm is proposed and applied to video tamper detection. Experimental results show that the algorithm can be applied to different types of video tamper detection, having obvious advantages with less labeled samples, effectively reducing the error rate of classifier and possessing good practical application value.
Article
A novel method for detecting the tampering of surveillance video is proposed. The purpose of the method is to detect removed object from video frames. The optical flow method is employed to extract motion characteristics. The objects are first detected using both the magnitudes and orientations of the motion vectors. The disordered distribution of the motion vectors is adopted as a sign of tampering. The method can identify and locate the tampered regions simultaneously. Simulation results demonstrate the efficiency of the proposed method.
Chapter
Full-text available
In the ongoing year, video falsification identification is a significant issue in video criminology. Unapproved changes in video outline causing debasement of genuineness and uprightness of inventiveness. With the progression in innovation, video preparing apparatuses and procedures are accessible for modifying the recordings for falsification. The adjustment or changes in current video is imperative to identify, since this video can be utilized in the validation procedure. Video authentication thus required to be checked. There are various ways by which video can be tempered, for example, frame insertion, deletion, duplication, copy and move, splicing and so on. This article presents forgery detection techniques like inter-frame forgery, intra-frame forgery & compression-based forgery detection that can be used for video tampering detection. Thorough analysis of newly developed techniques, passive video forgery detection is helpful for finding the problems and getting out new opportunities in the area of passive video forgery detection.
Chapter
Frame duplication is a common way of digital video forgeries. State-of-the-art approaches of duplication detection usually suffer from heavy computational load. In this paper, the authors propose a new algorithm to detect duplicated frames based on video sub-sequence fingerprints. The fingerprints employed are extracted from the DCT coefficients of the temporally informative representative images (TIRIs) of the sub-sequences. Compared with other similar algorithms, this study focuses on improving fingerprints representing video sub-sequences and introducing a simple metric for the matching of video sub-sequences. Experimental results show that the proposed algorithm overall outperforms three related duplication forgery detection algorithms in terms of computational efficiency, detection accuracy and robustness against common video operations like compression and brightness change.
Chapter
Local object removal on video can directly affect our understanding and cognition of the video content without changing the motion continuity of other moving objects in the same video frame. Forgers can use video editing tools or certain inpainting techniques to remove undesired objects easily for covering up the truth. In this paper, we present a new approach based on spatio-temporal LBP coherence analysis for detection and localization of forged regions, which are generated by removing unwanted objects from the video. The proposed method starts with frames alignment to handle camera motion. And then the coherence analysis on the spatial LBP operator between two adjacent frames is performed to find the possible forged region. Finally, the temporal LBP operator is utilized to remove the false positives so as to obtain the final abnormal area. Two common region-level inpainting methods are adopted to simulate two different types of forgery processes for performance evaluation of our scheme. The experimental results prove that our method is effective in detecting and locating the forged regions and superior to the existing two approaches.
Article
To increase the temporal continuity of low frame-rate videos, Motion-Compensated Frame-Rate Up-Conversion (MC-FRUC), which is a special frame based video editing manipulation, can be employed to synthesize new intermediate frame between two successive frames. However, MC-FRUC can also be utilized to fake high frame-rate videos causing the wastes of storage space or users misleading. Although existing MC-FRUC detectors can obtain desirable performance for uncompressed videos or compressed videos with high perceptual quality, theirs performance degrades when test videos are encoded with higher quantization parameters. To deal with this problem, this paper presents a new optical flow-based detection method. Our method is divided into four steps. First, the forward or backward optical flow map is estimated by optical flow algorithm between the candidate frame, and its previous frame or following frame, respectively. Second, the prediction residue is calculated on the basis of these estimated optical flow maps to eliminate the side effect of texture information in the non-motion regions and the motion regions. Third, Markov statistic features are extracted. Finally, these features are fed into the ensemble classifier for identification of interpolated frames. We test different types of MC-FRUC methods under higher quantization parameters, and the results have shown the effectiveness of the proposed method compared with the existing relative ones.
Article
As self-driving vehicles become increasingly popular, new generations of attackers will seek to exploit vulnerabilities introduced by the technologies that underpin such vehicles for a range of motivations (e.g. curiosity, criminally-motivated, financially-motivated and state-sponsored). For example, vulnerabilities in self-driving vehicles may be exploited to be used in terrorist attacks such as driving into places of mass gatherings (i.e. using driverless vehicles as weapons to cause death or serious bodily injury). This survey presents a categorized summary of security methodologies developed to secure sensing, positioning, vision, and network technologies that can be equipped in driverless-vehicles. These technologies have the potential to benefit their security from tailored machine learning models. Future research opportunities are also identified.
Conference Paper
In this paper we present a passive novel approach to detect and temporally localize video inpainting forgery based on optical flow consistency. The proposed algorithm comprises of two stages. In the first step, it detects whether the given video is inpainted or authentic using optical flow and in the second step temporal localization is performed. In order to evaluate the robustness of the proposed algorithm, experiments are performed against two popular and efficient inpainting techniques. We test our algorithm on comprehensive public datasets like PETS and SULFA. Experiments show that our approach is effective in detecting two popular inpainting types with good accuracy.
Chapter
This paper presents a method for detecting the removed object in video captured by stationary camera. The method is based on an observation that the removed object, while not distinguishable by human eyes, leaves artifacts that can be detected by computers. In this paper, the block based motion estimation method is employed to extract motion information from adjacent video frames. Then the magnitude and orientation of the motion vectors are used to differentiate the authentic region and the forged region. By exploring the discrepancies in motion vectors, the position of the removed object can be revealed. The efficiency of the proposed method is demonstrated by experiments.
Conference Paper
New generation video codecs are designed to improve coding efficiency with respect to previous standards and to support the latest hardware and applications. High Efficiency Video Coding (HEVC) is the successor of Advanced Video Coding (AVC), which is by far the most adopted standard worldwide. To promote the new standard, producers are re-releasing recent movies in HEVC format. In such a scenario, a fraudulent provider that does not own the original uncompressed data could sell old, lower quality AVC content re-encoded as if it were natively HEVC. Furthermore, with several hundred hours of video content uploaded every minute, it is not unlikely that re-edited low quality clips are labelled as HEVC to increase popularity and revenues from advertising. We tackle with these and similar issues by proposing a forensic technique to detect whether a HEVC sequence was obtained from an uncompressed sequence or by re-encoding an existing AVC sequence.
Article
Detection of object-based video forgery is receiving attention in recent years. However, until recently, dominant object-based forgery detectors are still based on hand-crafted features and their performances are not satisfactory. In this paper, we propose a novel hybrid deep-learning network which for the first time incorporates two-dimensional/three-dimensional convolutional neural network and recurrent neural network for object-based video forgery detection in videos with advanced encoding formats. Please note that the proposed framework is a full end-to-end data-driven solution. It is comprised of a specifically initialized three-dimensional convolutional layer which tries to mix up primitive intra-frame and inter-frame features, a two-dimensional CNN which tries to extract low-dimensional intra-frame features, and a four-layer bi-directional LSTM network which tries to catch high-level temporal features. Using this way, our proposed approach catches the intra-frame and inter-frame inherent properties of a target video with a united framework. The extensive experiments conducted on the largest object-based forged video database ever reported in the literature show that our hybrid framework achieves superior performance in forged video detection and forged segment localization. Moreover, the experiments conducted on datasets of videos with degraded quality demonstrated that our proposed framework is more robust in real-life scenarios.
Article
Frame duplication is a common way of digital video forgeries. State-of-the-art approaches of duplication detection usually suffer from heavy computational load. In this paper, the authors propose a new algorithm to detect duplicated frames based on video sub-sequence fingerprints. The fingerprints employed are extracted from the DCT coefficients of the temporally informative representative images (TIRIs) of the sub-sequences. Compared with other similar algorithms, this study focuses on improving fingerprints representing video sub-sequences and introducing a simple metric for the matching of video sub-sequences. Experimental results show that the proposed algorithm overall outperforms three related duplication forgery detection algorithms in terms of computational efficiency, detection accuracy and robustness against common video operations like compression and brightness change.
Article
Full-text available
Image inpainting or image completion is the technique that automatically restores/completes removed areas in an image. When dealing with a similar problem in video, not only should a robust tracking algorithm be used, but the temporal continuity among video frames also needs to be taken into account, especially when the video has camera motions such as zooming and tilting. In this paper, we extend an exemplar-based image inpainting algorithm by incorporating an improved patch matching strategy for video inpainting. In our proposed algorithm, different motion segments with different temporal continuity call for different candidate patches, which are used to inpaint holes after a selected video object is tracked and removed. The proposed new video inpainting algorithm produces very few ldquoghost shadows,rdquo which were produced by most image inpainting algorithms directly applied on video. Our experiments use different types of videos, including cartoon, video from games, and video from digital camera with different camera motions. Our demonstration at http://member.mine.tku.edu.tw/www/T_CSVT/web/shows the promising results.
Conference Paper
Full-text available
The recent development of video editing techniques enables us to create realistic synthesized videos. Therefore using video data as evidence in places such as a court of law requires a method to detect forged videos. In this paper we propose an approach to detect suspicious regions in video recorded from a static scene by using noise character- istics. The image signal contains irradiance-dependent noise where the relation between irradiance and noise depends on some parameters; they include inherent parameters of a camera such as quantum efficiency and a response function, and recording parameters such as exposure and elec- tric gain. Forged regions from another video camera taken under different conditions can be differentiated when the noise characteristics of the re- gions are inconsistent with the rest of the video.
Conference Paper
Full-text available
We propose a new approach for locating forged regions in a video using correlation of noise residue. In our method, block-level correlation values of noise residual are extracted as a feature for classification. We model the distribution of correlation of temporal noise residue in a forged video as a Gaussian mixture model (GMM). We propose a two- step scheme to estimate the model parameters. Consequently, a Bayesian classifier is used to find the optimal threshold value based on the estimated parameters. Two video inpainting schemes are used to simulate two different types of forgery processes for performance evaluation. Simulation results show that our method achieves promising accuracy in video forgery detection.
Conference Paper
Full-text available
Image in-painting or image completion removes objects from a photo and automatically produces a visually pleasant result. However, to remove objects from a video, the resulting video may have ghost shadows even each individual frame is in-painted properly. We use motion estimation algorithm to separate objects and backgrounds into several layers. Objects in separated layers are in-painted from back to front layers, with a consideration of the temporal continuity of motion segments among different frames. The resulting video is visually more pleasant with most ghost shadows removed. Interested readers are welcome to look at our demonstration Website at http://www.mine.tku.edu.tw/demo.
Article
Full-text available
A framework for inpainting missing parts of a video sequence recorded with a moving or stationary camera is presented in this work. The region to be inpainted is general: it may be still or moving, in the background or in the foreground, it may occlude one object and be occluded by some other object. The algorithm consists of a simple preprocessing stage and two steps of video inpainting. In the preprocessing stage, we roughly segment each frame into foreground and background. We use this segmentation to build three image mosaics that help to produce time consistent results and also improve the performance of the algorithm by reducing the search space. In the first video inpainting step, we reconstruct moving objects in the foreground that are "occluded" by the region to be inpainted. To this end, we fill the gap as much as possible by copying information from the moving foreground in other frames, using a priority-based scheme. In the second step, we inpaint the remaining hole with the background. To accomplish this, we first align the frames and directly copy when possible. The remaining pixels are filled in by extending spatial texture synthesis techniques to the spatiotemporal domain. The proposed framework has several advantages over state-of-the-art algorithms that deal with similar types of data and constraints. It permits some camera motion, is simple to implement, fast, does not require statistical models of background nor foreground, works well in the presence of rich and cluttered backgrounds, and the results show that there is no visible blurring or motion artifacts. A number of real examples taken with a consumer hand-held camera are shown supporting these findings.