December 2024
·
6 Reads
What is this page?
This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.
Publications (33)
November 2024
·
10 Reads
July 2024
·
60 Reads
·
1 Citation
Language and Linguistics Compass
Deepfakes, particularly audio deepfakes, have become pervasive and pose unique, ever‐changing threats to society. This paper reviews the current research landscape on audio deepfakes. We assert that limitations of existing approaches to deepfake detection and discernment are areas where (socio)linguists can directly contribute to helping address the societal challenge of audio deepfakes. In particular, incorporating expert knowledge and developing techniques that everyday listeners can use to avoid deception are promising pathways for (socio)linguistics. Further opportunities exist for developing benevolent applications of this technology through generative AI methods as well.
March 2024
·
5 Reads
·
2 Citations
January 2024
·
51 Reads
Proceedings of the AAAI Symposium Series
We present an innovative approach to auto-annotate Expert Defined Linguistic Features (EDLFs) as subsequences in audio time series to improve audio deepfake discernment. In our prior work, these linguistic features – namely pitch, pause, breath, consonant release bursts, and overall audio quality, labeled by experts on the entire audio signal – have been shown to improve detection of audio deepfakes with AI algorithms. We now expand our approach to pilot a way to auto annotate subsequences in the time series that correspond to each EDLF. We developed an ensemble of discords, i.e. anomalies in time series, detected using matrix profiles across multiple discord lengths to identify multiple types of EDLFs. Working closely with linguistic experts, we evaluated where discords overlapped with EDLFs in the audio signal data. Our ensemble method to detect discords across multiple discord lengths achieves much higher accuracy than using individual discord lengths to detect EDLFs. With this approach and domain validation we establish the feasibility of using time series subsequences to capture EDLFs to supplement annotation by domain experts, for improved audio deepfake detection.
October 2023
·
36 Reads
·
7 Citations
July 2023
March 2023
·
2 Reads
January 2023
·
1,712 Reads
·
61 Citations
Frontiers in Big Data
A deepfake is content or material that is synthetically generated or manipulated using artificial intelligence (AI) methods, to be passed off as real and can include audio, video, image, and text synthesis. The key difference between manual editing and deepfakes is that deepfakes are AI generated or AI manipulated and closely resemble authentic artifacts. In some cases, deepfakes can be fabricated using AI-generated content in its entirety. Deepfakes have started to have a major impact on society with more generation mechanisms emerging everyday. This article makes a contribution in understanding the landscape of deepfakes, and their detection and generation methods. We evaluate various categories of deepfakes especially in audio. The purpose of this survey is to provide readers with a deeper understanding of (1) different deepfake categories; (2) how they could be created and detected; (3) more specifically, how audio deepfakes are created and detected in more detail, which is the main focus of this paper. We found that generative adversarial networks (GANs), convolutional neural networks (CNNs), and deep neural networks (DNNs) are common ways of creating and detecting deepfakes. In our evaluation of over 150 methods, we found that the majority of the focus is on video deepfakes, and, in particular, the generation of video deepfakes. We found that for text deepfakes, there are more generation methods but very few robust methods for detection, including fake news detection, which has become a controversial area of research because of the potential heavy overlaps with human generation of fake content. Our study reveals a clear need to research audio deepfakes and particularly detection of audio deepfakes. This survey has been conducted with a different perspective, compared to existing survey papers that mostly focus on just video and image deepfakes. This survey mainly focuses on audio deepfakes that are overlooked in most of the existing surveys. This article's most important contribution is to critically analyze and provide a unique source of audio deepfake research, mostly ranging from 2016 to 2021. To the best of our knowledge, this is the first survey focusing on audio deepfakes generation and detection in English.
September 2022
·
2 Reads
·
3 Citations
Citations (14)
... This work indicates a promising new avenue for improving traditional detection approaches. The as-yet relatively unexplored frontier of fake audio detection in multi-speaker conversational settings, such as call center recordings featuring interactions with counterfeit representatives and customers, would likely also benefit from (socio)linguistic insight (27). ...
- Citing Article
July 2024
Language and Linguistics Compass
... During the Fordism period, the primary focus was on manual skills, with little emphasis on soft skills [65]. However, the modern job market has shifted toward creative roles [66], with positions like software engineers, and data scientists becoming some of the most sought-after [67], [68]. In these roles, soft skills have become just as essential as technical expertise-if not more so, particularly when working directly with people [69]. ...
- Citing Conference Paper
March 2024
... Based on the type of media, deepfakes can be categorised into four modes: text, image, audio and video (Khan et al., 2022). Correspondingly, DL models have also been increasingly applied to various domains, including computer vision, audio recognition, machine translation, and natural language processing, and have demonstrated promising performance in detecting deepfakes (Khanjani, 2023;Kumar and Taylor, 2023;Patel et al., 2023). This is mainly reflected in practice, by integrating DL/ML models and computer vision-based techniques, the most common deepfakes (i.e., images and videos) can already be easily identified: For instance, convolutional neural networks (CNNs) have been widely employed to capture subtle manipulation traces in deepfake images and videos (Sudhakar and Shanthi, 2023;Guo et al., 2022); And other DL techniques, such as generative adversarial networks (GANs), autoencoders, and long short-term memory (LSTM) networks (Reddy et al., 2023;Patel et al., 2023) have also been extensively applied, which have consistently outperformed traditional ML models in detection tasks. ...
- Citing Conference Paper
October 2023
... Yet, these same capabilities lower the barriers to producing deceptive content. Audio deepfakes, for example, can clone voices with remarkable fidelity and manipulate speech inflections to produce content that can easily fool human listeners (Khanjani, Watson, & Janeja, 2023). While the original focus of deepfake technology centered on visual media, the audio domain has proven equally susceptible to highly realistic alterations that can lead to fraudulent schemes and erosion of trust. ...
- Citing Article
- Full-text available
January 2023
Frontiers in Big Data
... These elements encompass the period of delay in response time, the level of organizing in which data exists, specification of an SQL environment required, kinds of anticipated analytics, particular kinds of visual illustrations that may be required and finally societal demands for safety as well as your organizational requirements. Various big data technologies might be selected according to these aspects [2]. This research paper investigates essential practices that organizations ought to adopt in order to create a virtual impenetrable box around their database servers (Comprehensive Database Security). ...
- Citing Article
August 2022
... APT Characteristics[3]. ...
- Citing Article
August 2022
... For instance, it is dangerous when passwords are identical across several platforms, thereby creating a single point of vulnerability. Also, saving passwords within the system or on paper may seem easier but can pose significant threats to security given that it is in a not completely safe area [6]. Likewise, mechanisms like two-factor authentication must be examined attentively regarding potential users who will utilize them. ...
- Citing Article
August 2022
... This is some useful information that we need to capture. Hence, in this situation symmetric coefficient would be used [8]. ...
- Citing Article
August 2022
... [1] proposed an attention-based LSTM ensemble that takes in multi-temporal, daily and monthly, data and predicts sea ice extent (SIE) for T + 1 timestep, achieving an RMSE of 4.9 × 10 6 km 2 . To explore the potential of probabilistic modeling approaches for forecasting sea ice and to aid uncertainty quantification, [2] performed a thorough comparative analysis of four probabilistic and two baseline machine learning and deep learning models and published benchmarking results for sea ice forecasting for multiple lead times on these models. They evaluated these models performance using RMSE error and R 2 scores and reported Gaussian Process Regression (GPR) to achieve the most competent results. ...
- Citing Conference Paper
July 2022
... To date, surgical intervention is the primary modality of management for non-compressible truncal hemorrhage [11], and effectively managing such injuries in the pre-hospital setting remains a significant challenge. To address this issue, several new therapeutic strategies such as abdominal insufflation [12], intraperitoneal devices [13], expandable foams [14][15][16][17], and hemostatic nanoparticles [18][19][20][21] have been proposed. Such modalities must be tested in large animal injury models before progressing to clinical application. ...
- Citing Article
July 2022
ACS Nano
