1 December 2023 in International Journal of Intelligent Computing and Information Sciences
Deception techniques play a crucial role in enhancing cybersecurity by misleading attackers and safeguarding critical systems. The strategic placement of decoys constructs an elaborate defense architecture that can effectively thwart unauthorized access. This paper presents a comprehensive survey of deception techniques from a research perspective, highlighting their classification, modeling methodologies, and deployment strategies. Additionally, it explores the major research issues associated with these techniques, including the challenge of maintaining the believability of decoys and the ethical implications of their use. Moreover, the paper investigates the role of Moving Target Defense (MTD) in cyber deception, emphasizing its dynamic nature and specifically the network environments. This paper goes beyond theoretical discussions and digs into the implementation details of real frameworks operating at four layers of the deception stack composed of the network, system, software, and data layers. The seamless integration between these layers is essential for creating a convincing deceptive environment. It categorizes these implementations into four main approaches and highlights the corresponding systems that have been developed, thus offering a roadmap for future research and development in this critical field of cybersecurity.
30 September 2024 in International Journal of Intelligent Computing and Information Sciences
The exponential growth in internet data usage has created a pressing demand for highly efficient Network Intrusion Detection Systems (NIDS) capable of scaling with ever-increasing bandwidths to safeguard sensitive information. A cornerstone of NIDS, packet inspection, hinges on the ability to rapidly identify and analyze patterns within incoming data streams. The more diverse and extensive the pattern database, the more robust and effective the NIDS becomes. While the parallel failure-less version of the Aho-Corasick (AC) algorithm provides maximum parallelism, it faces significant memory constraints due to the large transition tables generated when dealing with a vast number of patterns. To mitigate this limitation and enhance the scalability of NIDS, we introduce a novel parallel failure-less compressed hashed variation of the Aho-Corasick algorithm. Our proposed approach leverages the power of compression and hashing techniques to significantly reduce memory consumption without compromising performance. Empirical evaluations demonstrate that our algorithm requires only a fraction (approximately the square root) of the memory footprint compared to the original parallel failure-less Aho-Corasick algorithm, making it a more practical and scalable solution for modern NIDS architectures.
8 February 2025 in Journal of Optics
1 December 2023 in International Journal of Intelligent Computing and Information Sciences
Face recognition technologies are rapidly becoming integral to a variety of applications, ranging from security systems to user authentication. This increasing reliance necessitates robust and accurate methods for face liveness detection. This paper presents and thoroughly evaluates two cutting-edge methods for face liveness detection: the Restrictive Voting approach and the Transfer Learning Approach. Our evaluation was performed using the Replay-Attack dataset. Various performance metrics were reported, including Accuracy, Precision, Recall, and F1-Score. Additionally, a comparative analysis was presented specifically for Half Total Error (HTER) and Equal Error Rate (EER), clearly indicating the superior performance of both methods compared to current state-of-the-art techniques. Remarkably, both methods achieved a zero False Acceptance Rate (FAR), thereby entirely negating the possibility of unauthorized access. These groundbreaking findings not only affirm the robustness of the introduced methods but also suggest their substantial potential for implementation in high-security, real-world scenarios, highlighting their unmatched excellence in face liveness detection.
26 May 2023 in International Journal of Communication Networks and Information Security (IJCNIS)
Face anti-spoofing has become widely used due to the increasing use of biometric authentication systems that rely on facial recognition. It is a critical issue in biometric authentication systems that aim to prevent unauthorized access. In this paper, we propose a modified version of majority voting that ensembles the votes of six classifiers for multiple video chunks to improve the accuracy of face anti-spoofing. Our approach involves sampling sub-videos of 2 seconds each with a one-second overlap and classifying each sub-video using multiple classifiers. We then ensemble the classifications for each sub-video across all classifiers to decide the complete video classification. We focus on the False Acceptance Rate (FAR) metric to highlight the importance of preventing unauthorized access. We evaluated our method using the Replay Attack dataset and achieved a zero FAR. We also reported the Half Total Error Rate (HTER) and Equal Error Rate (EER) and gained a better result than most state-of-the-art methods. Our experimental results show that our proposed method significantly reduces the FAR, which is crucial for real-world face anti-spoofing applications.