Dipankar DasguptaThe University of Memphis | U of M · Department of Computer Science
Dipankar Dasgupta
Doctor of Philosophy
About
273
Publications
144,530
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
13,281
Citations
Introduction
I have more than 25 years of experience in research which cover broad areas of innovating computational models for Information Technology, in particular, design and development of intelligent software solutions inspired by natural processes. My multidisciplinary research resulted in more than 250 publications and two textbooks, two edited volumes and several co-edited journals and conference proceedings. My latest book Advances in User Authentication published by Springer, Inc, August 2017.
Publications
Publications (273)
Generative Adversarial Networks (GAN) excel in diverse applications like image enhancement, manipulation, generating images and videos from text, etc. Yet, training GANs with large datasets remains computationally intensive for standalone systems. Synchronization issues between the generator and discriminator lead to unstable training, poor converg...
Evasion attacks on cyber-enabled machine learning (ML) models have recently gained significant traction for their ability to swiftly compel ML models to deviate from their original decisions without substantially affecting model accuracy during the testing phase. In this article, we initially present a meticulously formulated theoretical framework...
p>Many applications of Generative AI (such as DALL-E, GPT-3, ChatGPT, etc.) are making headline news in recent months and have been receiving both praise and criticism for their far reaching implications. Some of these applications include query responses, language translation, text to images and videos, composing stories, essays, creating arts and...
Many applications of Generative AI (such as DALL-E, GPT-3, ChatGPT, etc.) are making headline news in recent months and have been receiving both praise and criticism for their far reaching implications. Some of these applications include query responses, language translation, text to images and videos, composing stories, essays, creating arts and m...
As grid-connected wind farms become more common in the modern power system, the question of how to maximize wind power generation while limiting downtime has been a common issue for researchers around the world. Due to the complexity of wind turbine systems and the difficulty to predict varying wind speeds, artificial intelligence (AI) and machine...
Generative Adversarial Network (GAN) investigations highlight new vulnerabilities and challenges to machine learning models' security and privacy. Different AI/ML applications are becoming vulnerable due to adversarial GAN techniques. This paper surveyed GAN variants and outlined cyber threats and defenses powered by generative adversarial networks...
Generative Adversarial Networks (GAN) and their several variants have not only been used for adversarial purposes but also used for extending the learning coverage of different AI/ML models. Most of these variants are
unconditional
and do not have enough control over their outputs.
Conditional
GANs (CGANs) have the ability to control their outp...
With the surge in the adoption of AI/ML techniques in industry, adversarial challenges are also on the rise and defense strategies need to be configured accordingly. While it is crucial to formulate new attack methods (similar to Fuzz testing) and devise novel defense strategies for coverage and robustness, it is also imperative to recognize who is...
Existing defense strategies against adversarial attacks (AAs) on AI/ML are primarily focused on examining the input data streams using a wide variety of filtering techniques. For instance, input filters are used to remove noisy, misleading, and out-of-class inputs along with a variety of attacks on learning systems. However, a single filter may not...
Dynamic wireless charging (DWC) is an emerging technology that allows electric vehicles (EVs) to be wirelessly charged while in motion. It is gaining significant momentum as it can potentially address the range limitation issue for EVs. However, due to significant power loss caused by wireless power transfer, improving charging efficiency remains a...
In all goal-oriented selection activities, the existence of a certain level of bias is unavoidable and may be desired for efficient AI-based decision support systems. However, a fair, independent comparison of all eligible entities is essential to alleviate explicit biasness in a competitive marketplace. For example, searching online for a good or...
Defenses against adversarial attacks are essential to ensure the reliability of machine-learning models as their applications are expanding in different domains. Existing ML defense techniques have several limitations in practical use. We proposed a trustworthy framework that employs an adaptive strategy to inspect both inputs and decisions. In par...
The Negative selection Algorithm (NSA) is one of the important methods in the field of Immunological Computation (or Artificial Immune Systems). Over the years, some progress was made which turns this algorithm (NSA) into an efficient approach to solve problems in different domain. This review takes into account these signs of progress during the l...
Various adversarial attack methods pose a threat to secure machine learning models. Pre-processing-based defense against adversarial input was not adequate, and they are vulnerable to adaptive attacks. Our study proposed a dynamic pre-process-based defense technique leveraging a Genetic Algorithm that can defend against traditional adaptive attacks...
Crypto-ransomware is the most prevalent form of modern malware, has affected various industries, demanding a significant amount of ransom. Mainly, small businesses, healthcare, education, and government sectors have been under continuous attacks by these adversaries. Various static and dynamic analysis techniques exist, but these methods become les...
Technology runs much of modern society’s daily functions due to how efficient, reliable, and easy it is to access and manage content anywhere at any time. This rapid growth has created an emphasis on cybersecurity to ensure data integrity in today’s digital realm and the future to come. Since more industries are relying on technology, cybersecurity...
We have seen a surge in research aims toward adversarial attacks and defenses in AI/ML systems. While it is crucial to formulate new attack methods and devise novel defense strategies for robustness, it is also imperative to recognize who is responsible for implementing, validating, and justifying the necessity of these defenses. In particular, whi...
The Negative selection Algorithm (NSA) is one of the important methods in the field of Immunological Computation (or Artificial Immune Systems). Over the years, some progress was made which turns this algorithm (NSA) into an efficient approach to solve problems in different domain. This review takes into account these signs of progress during the l...
The Supervisory control and data acquisition (SCADA) systems have been continuously leveraging the evolution of network architecture, communication protocols, next-generation communication techniques (5G, 6G, Wi-Fi 6), and the internet of things (IoT). However, SCADA system has become the most profitable and alluring target for ransomware attackers...
With the increased popularity of Machine Learning (ML) in real-world applications, adversarial attacks are emerging to subvert the ML-based systems. Existing adversarial defense techniques are ineffective against adaptive adversarial attacks since these are highly depend on prior knowledge of adversarial attacks and ML model's specificity. We propo...
Adversarial attacks are considered security risks for Artificial Intelligence-based systems. Researchers have been studying different defense techniques appropriate for adversarial attacks. Evaluation strategies of these attacks and corresponding defenses are primarily conducted on trivial benchmark analysis. We have observed that most of these ana...
Ransomware attacks are taking advantage of the ongoing pandemics and attacking the vulnerable systems in business, health sector, education, insurance, bank, and government sectors. Various approaches have been proposed to combat ransomware, but the dynamic nature of malware writers often bypasses the security checkpoints. There are commercial tool...
Modern deep learning models for the computer vision domain are vulnerable against adversarial attacks. Image prepossessing technique based defense against malicious input is currently considered obsolete as this defense is not effective against all types of attacks. The advanced adaptive attack can easily defeat pre-processing based defenses. In th...
Today's world is highly network interconnected owing to the pervasiveness of small personal devices (e.g., smartphones) as well as large computing devices or services (e.g., cloud computing or online banking), and thereby each passing minute millions of data bytes are being generated, processed, exchanged, shared, and utilized to yield outcomes in...
ML-synthesized face samples, frequently called DeepFakes, is a serious issue menacing the integrity of information on the Internet and face recognition systems. One of the main defenses against face manipulations is DeepFakes detection. In this paper, we first created a new DeepFakes dataset using a publicly available MUCT database, which contains...
Ransomware attacks increased within the past few years resulting huge financial losses to various businesses across the globe. To overcome the ransomware attacks, executables (or binary files) are converted back to assembly-level language or source code for further examination. In this work, we propose a novel ransomware detection method based on j...
Developing secure machine learning models from adversarial examples is challenging as various methods are continually being developed to generate adversarial attacks. In this work, we propose an evolutionary approach to automatically determine Image Processing Techniques Sequence (IPTS) for detecting malicious inputs. Accordingly, we first used a d...
In all goal-oriented selection activities, an existence of certain level of bias is unavoidable and may be desired for efficient artificial intelligence based decision support systems. However, a fair independent comparison of all eligible entities is essential to alleviate explicit bias in competitive marketplace. For example, searching online for...
Biometrics is now being principally employed in many daily applications ranging from the border crossing to mobile user authentication. In the high-security scenarios, biometrics require stringent accuracy and performance criteria. Towards this aim, multi-biometric systems that fuse the evidences from multiple sources of biometric have exhibited to...
Shamir's Secret sharing [1] is a quantum attack proof algorithm and is used heavily for secret sharing. But it can also be used for authentication protocols as a replacement of hashing. In this paper, we propose an authentication protocol which will use Shamir's secret sharing method to authenticate with server. Hashing may not be able to hide data...
The global proliferation of affordable photographing devices and readily-available face image and video editing software has caused a remarkable rise in face manipulations, e.g., altering face skin color using FaceApp. Such synthetic manipulations are becoming a very perilous problem, as altered faces not only can fool human experts but also have d...
A system and related methods for providing greater security and control over access to classified files and documents and other forms of sensitive information based upon a multiuser permission strategy centering on organizational structure .
Multi-level Ransomware Detection Framework using NLP and Machine Learning
Ransomware attacks in recent years have proved expensive due to significant damages and obstructions these caused in various sectors such as health, insurance, business, and education. Several malware detection methods have been proposed to uncover different malware families, but the problem remained unsolved due to the continuously evolving malwar...
In recent years, there has been an exponential increase in photo and video manipulation by easy-to-use editing tools (e.g., Photoshop). Especially, 'face digital manipulations' (e.g., face swapping) is a critical issue for automated face recognition systems (AFRSs) as it detrimentally effects the AFRS' performance. Also, the advent of powerful deep...
Ransomware attacks increased in recent years causing significant damages and disruptions to businesses. Forensic analysis such as reverse engineering of executables (or binary files) is the common practice of examining such malware characteristics. In this work, we developed a reverse engineering framework incorporating feature generation engines a...
The report starts with an overview of the blockchain security system and then highlights the specific security threats and summarizes them. We review with some comments and possible research direction. This survey, we examines the security issues of blockchain model related technologies and their applications. The blockchain is considered a still g...
In this paper we present a survey of three recent developments in biometric user authentication based on physical human characteristics that are less prone to natural or intentional changes than other currently used techniques: thermal vein signatures, DNA and EEG brainprint obtained by stimulating the brain with cognitive events. This paper argues...
In US Multimarket trading is very popular for investors, professionals and high frequency traders. This research focuses on exchanges and apply an association rule mining, an unsupervised machine learning technique for discovering the relationships between the stock exchanges. In this work we used FP-growth algorithm for finding the relation betwee...
Forensic analysis of executables or binary files is the common practice of detecting malware characteristics. Reverse engineering is performed on executables at different levels such as raw binaries, assembly codes, libraries, and function calls to better analysis and interpret the purpose of code segments.
In this work, we apply data-mining tech...
Online media is now a significant carrier for quicker and ubiquitous diffusion of information. Any user in social media can post contents, provide news blogs, and engage in debate or opinion nowadays. Most of the posted pieces of information on social media are useful while some are fallacious and insulting to others. Keeping the promise of freedom...
The increased use of cyber-enabled systems and Internet-of-Things (IoT) led to a massive amount of data with different structures. Most big data solutions are built on top of the Hadoop eco-system or use its distributed file system (HDFS). However, studies have shown inefficiency in such systems when dealing with today's data. Some research overcam...
Exfiltration of sensitive data and intellectual property theft have increased to a significant level affecting both government agencies as well as small to large businesses. One of the major reasons of data breaches is malicious insiders who have the access rights, knowledge of data values and technical know-how of escalating their privileges in la...
Mobile health (mHealth) is being recognized as an innovative approach to deliver health care in an accessible, portable and cost effective manner. Despite the numerous benefits associated with the use of mobile devices, there are major concerns with mhealth in the area of privacy and security. These aspects need to be considered at every stages of...
Clustering algorithms have emerged as a powerful learning tool to accurately analyze the massive amount of data generated by current applications and smart technologies. Precisely, their main objective is to categorize data into clusters such that objects are grouped in the same cluster when they are similar according to specific metrics. There is...
In today's highly intertwined network society, the demand for big data processing frameworks is continuously growing. The widely adopted model to process big data is parallel and distributed computing. This paper documents the significant progress achieved in the field of distributed computing frameworks, particularly Apache Hama, a top level proje...
Most insider attacks done by people who have the knowledge and technical know-how of launching such attacks. This topic has long been studied and many detection techniques were proposed to deal with insider threats. This short paper summarized and classified insider threat detection techniques based on strategies used for detection.
Smart grid is a complex cyber physical system containing numerous and variety of sources, devices, controllers and loads. Communication/Information infrastructure is the backbone of the smart grid system where different grid components are connected with each other through this structure. Therefore, the drawbacks of the information technology relat...
The cyberspace has become an integral part of modern day life-social, economic, political, religious, medical and other aspects. Without the availability of the Internet today's businesses, government and society cannot function properly. Moreover, different online social media and blogosphere are bringing people together, providing platforms to sh...
The important backbone of the smart grid is the cyber/information infrastructure, which is primarily used to communicate with different grid components. A smart grid is a complex cyber physical system containing a numerous and variety number of sources, devices, controllers and loads. Therefore, the smart grid is vulnerable to grid related disturba...
Surveys show that more than 80% authentication systems are password based and these systems are increasingly under direct and indirect attacks. In an effort to protect the Positive Authentication System (PAS), the negative authentication concept was introduced [9]. Here, the representation space of password profile is called self-region; any elemen...
Many organizations are adopting cloud services to reduce their computing cost and increase the flexibility of their IT infrastructure. As cloud services are moving to the mainstream to meet major computing needs, the issues of ownership and chain of custody of customer data are becoming primary responsibilities of providers. Therefore, security req...
Cell signaling mechanism provides robust immune response and protects our body from a wide variety of pathogens. This work attempts to develop an artificial signaling model inspired by biological signaling process and derived abstractions. In this paper, we described various aspects of immune cell signaling and their integration towards a system-le...
This work explores how various approaches are being used to strengthen password-based authentication mechanism by obfuscating user password credential (positive identification) while allowing access through different (derived) validating strategies. We first discussed some existing methods followed by our proposed approaches, experiments and compar...
In this article, we describe an analysis of social network data set that was collected from the Live Journal (LJ) site during autumn 2013. Initially, we collected 114 politically active LJ user profiles, and friends of their friends using the graph search, i.e. those users who are two hops away from those on the original list. A graph was formed fr...
Cyber-security issues affect organisations at all levels. In this article, we will discuss how to apply a visualisation and event correlation tool to facilitate the analysis of data, understanding of data, and dissemination of information to all affected parties. The visualisation shows an overall view of security events or storms that are occurrin...
Many organizations are adopting cloud services to reduce their computing cost and increase the flexibility of their IT infrastructure. As cloud services are moving to the mainstream to meet major computing needs, the issues of ownership and chain of custody of customer data are becoming primary responsibilities of providers. Therefore, security req...
The biological immune system is a robust, complex, adaptive system that defends the body from foreign pathogens. It is able to categorize all cells (or molecules) within the body asself or nonself substances. It does this with the help of a distributed task force that has theintelligence to take action from a local and also a global perspective usi...