Jagdeep Singh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jagdeep Singh has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Isaac Woungang
Toronto Metropolitan University, Toronto, Canada
12 shared publications - Sanjay Kumar Dhurandher
Netaji Subhas University of Technology
8 shared publications Sanjay Kumar Dhurandher
Netaji Subhas University of Technology
5 shared publicationsSanjay K. Dhurandher
Netaji Subhas University of Technology
3 shared publicationsGeetanshu Gupta
Netaji Subhas Institute of Technology
2 shared publications- Khuram Khalid
Ryerson University
2 shared publications
Latest Publications
- 12 August 2026
- Published by Springer Nature
- p. 152-164
A Machine Learning-Based Routing Protocol for DTN-Assisted Flying Ad-Hoc Networks
- 12 August 2026
- Published by Springer Nature
- p. 152-164
A Machine Learning-Based Routing Protocol for DTN-Assisted Flying Ad-Hoc Networks
- 1 June 2026
- Published by Springer Nature
- p. 361-373
Adversarial Explanation Training for Trustworthy XAI in Cybersecurity: Attacks, Defenses, and Human-Centric Evaluation
- 1 June 2026
- Published by Springer Nature
- p. 361-373
Adversarial Explanation Training for Trustworthy XAI in Cybersecurity: Attacks, Defenses, and Human-Centric Evaluation
- Open Access
- 7 February 2026
- Published by Institute of Central Computation and Knowledge Inc. in Journal of Reliable and Secure Computing
- Vol. 2 (1) , 27-38
A Novel System for Detecting Model Poisoning Attacks in Federated Learning
Federated learning (FL) enables decentralized model training and enhances user privacy by keeping data on local devices. Despite these advantages, FL remains vulnerable to sophisticated adversarial attacks. Federated recommender systems (FRS), an important application of FL, are particularly susceptible to threats such as model poisoning. In this paper, we propose DyMUSA, a novel model poisoning attack tailored for FRS. DyMUSA exploits systemic vulnerabilities through dynamic user selection and adaptive poisoning strategies. Specifically, it leverages the Isolation Forest algorithm to identify anomalous users and generate poisoned gradients that compromise the integrity of the recommender system. Experiments conducted on real-world datasets demonstrate that DyMUSA significantly increases the exposure of targeted items while maintaining minimal impact on overall system performance.
- 7 February 2026
- Published by Institute of Central Computation and Knowledge Inc. in Journal of Reliable and Secure Computing
- Vol. 2 (1) , 27-38
Open AccessA Novel System for Detecting Model Poisoning Attacks in Federated Learning
Federated learning (FL) enables decentralized model training and enhances user privacy by keeping data on local devices. Despite these advantages, FL remains vulnerable to sophisticated adversarial attacks. Federated recommender systems (FRS), an important application of FL, are particularly susceptible to threats such as model poisoning. In this paper, we propose DyMUSA, a novel model poisoning attack tailored for FRS. DyMUSA exploits systemic vulnerabilities through dynamic user selection and adaptive poisoning strategies. Specifically, it leverages the Isolation Forest algorithm to identify anomalous users and generate poisoned gradients that compromise the integrity of the recommender system. Experiments conducted on real-world datasets demonstrate that DyMUSA significantly increases the exposure of targeted items while maintaining minimal impact on overall system performance.
- Open Access
An Evolutionary Game Theory and Reinforcement Learning-Based Security Protocol for Intermittently Connected Wireless Networks
Intermittently Connected Wireless Networks (ICWNs) are characterized by dynamic node mobility and the absence of persistent end-to-end paths, making them highly susceptible to security threats. This paper proposes a novel secure routing protocol, called the Evolutionary Game Theoretic model with Reinforcement Learning (EGT-RL), designed to provide adaptive and resilient protection against blackhole attacks in such networks. EGT-RL integrates Q-learning for dynamic threat assessment with evolutionary game theory to model and influence node behavior over time. Simulation results, based on both synthetic and real-world mobility traces, show that EGT-RL significantly outperforms three benchmark protocols in delivery ratio, packet drops, end-to-end latency, and communication overhead.
Open AccessAn Evolutionary Game Theory and Reinforcement Learning-Based Security Protocol for Intermittently Connected Wireless Networks
Intermittently Connected Wireless Networks (ICWNs) are characterized by dynamic node mobility and the absence of persistent end-to-end paths, making them highly susceptible to security threats. This paper proposes a novel secure routing protocol, called the Evolutionary Game Theoretic model with Reinforcement Learning (EGT-RL), designed to provide adaptive and resilient protection against blackhole attacks in such networks. EGT-RL integrates Q-learning for dynamic threat assessment with evolutionary game theory to model and influence node behavior over time. Simulation results, based on both synthetic and real-world mobility traces, show that EGT-RL significantly outperforms three benchmark protocols in delivery ratio, packet drops, end-to-end latency, and communication overhead.
- 2 January 2026
- Published by Springer Nature
- p. 577-591
Dynamic Trust and Reputation-Based Framework for Opportunistic Networks
- 2 January 2026
- Published by Springer Nature
- p. 577-591
Dynamic Trust and Reputation-Based Framework for Opportunistic Networks
- 26 August 2025
- Published by Wiley in International Journal of Communication Systems
- Vol. 38 (14)
Optimization‐Driven Localization in Wireless Sensor Networks: A Comprehensive Review of Single and Hybrid Metaheuristic Approaches
Wireless sensor networks (WSNs), consisting of numerous smart sensor nodes, are increasingly integrated into domains including battlefield surveillance, environmental monitoring, industrial automation, and smart cities. Precise sensor positioning ensures effective communication, optimizes energy consumption, and maintains dependable system performance. However, the dynamic nature of WSNs, characterized by random node deployment, mobility, energy constraints, and environmental unpredictability, poses significant localization challenges. Traditional techniques often fall short under these conditions. Although several studies have proposed optimization‐based approaches for localization, there is a lack of consolidated, up‐to‐date reviews that compare single and hybrid metaheuristic techniques across performance metrics. Additionally, past reviews often overlook recent trends, bibliometric insights, and evolving research challenges. This study provides an in‐depth survey of positioning methods employed in WSNs, focusing on single and hybrid metaheuristic methods. It introduces a year‐wise comparative framework that evaluates these techniques based on accuracy, energy consumption, localization error, computational complexity, scalability, and node distribution. A bibliometric analysis using the Web of Science database further explores research trends, identifies leading contributors, and tracks the evolution of keywords. Tables and figures summarize the advantages, drawbacks, and enhancements of each approach. The study highlights that hybrid optimization models consistently outperform single‐method techniques, achieving up to 25% lower localization error and improved energy efficiency. The findings also identify future directions in software‐defined networking and ML‐integrated hybrid models, providing a strong foundation for advancing localization in next‐generation WSNs.
- 26 August 2025
- Published by Wiley in International Journal of Communication Systems
- Vol. 38 (14)
Optimization‐Driven Localization in Wireless Sensor Networks: A Comprehensive Review of Single and Hybrid Metaheuristic Approaches
Wireless sensor networks (WSNs), consisting of numerous smart sensor nodes, are increasingly integrated into domains including battlefield surveillance, environmental monitoring, industrial automation, and smart cities. Precise sensor positioning ensures effective communication, optimizes energy consumption, and maintains dependable system performance. However, the dynamic nature of WSNs, characterized by random node deployment, mobility, energy constraints, and environmental unpredictability, poses significant localization challenges. Traditional techniques often fall short under these conditions. Although several studies have proposed optimization‐based approaches for localization, there is a lack of consolidated, up‐to‐date reviews that compare single and hybrid metaheuristic techniques across performance metrics. Additionally, past reviews often overlook recent trends, bibliometric insights, and evolving research challenges. This study provides an in‐depth survey of positioning methods employed in WSNs, focusing on single and hybrid metaheuristic methods. It introduces a year‐wise comparative framework that evaluates these techniques based on accuracy, energy consumption, localization error, computational complexity, scalability, and node distribution. A bibliometric analysis using the Web of Science database further explores research trends, identifies leading contributors, and tracks the evolution of keywords. Tables and figures summarize the advantages, drawbacks, and enhancements of each approach. The study highlights that hybrid optimization models consistently outperform single‐method techniques, achieving up to 25% lower localization error and improved energy efficiency. The findings also identify future directions in software‐defined networking and ML‐integrated hybrid models, providing a strong foundation for advancing localization in next‐generation WSNs.
- 23 April 2025
- Published by Springer Nature
- p. 244-256
A Secure Routing Protocol for Opportunistic Networks
- 23 April 2025
- Published by Springer Nature
- p. 244-256
A Secure Routing Protocol for Opportunistic Networks
- Open Access
Context-Aware Trust and Reputation Routing Protocol for Opportunistic IoT Networks
In opportunistic IoT (OppIoT) networks, non-cooperative nodes present a significant challenge to the data forwarding process, leading to increased packet loss and communication delays. This paper proposes a novel Context-Aware Trust and Reputation Routing (CATR) protocol for opportunistic IoT networks, which leverages the probability density function of the beta distribution and some contextual factors, to dynamically compute the trust and reputation values of nodes, leading to efficient data dissemination, where malicious nodes are effectively identified and bypassed during that process. Simulation experiments using the ONE simulator show that CATR is superior to the Epidemic protocol, the so-called beta-based trust and reputation evaluation system (denoted BTRES), and the secure and privacy-preserving structure in opportunistic networks (denoted PPHB+), achieving an improvement of 22%, 15%, and 9% in terms of average latency, number of messages dropped, and average hop count, respectively, under varying number of nodes, buffer size, time to live, and message generation interval.
Open AccessContext-Aware Trust and Reputation Routing Protocol for Opportunistic IoT Networks
In opportunistic IoT (OppIoT) networks, non-cooperative nodes present a significant challenge to the data forwarding process, leading to increased packet loss and communication delays. This paper proposes a novel Context-Aware Trust and Reputation Routing (CATR) protocol for opportunistic IoT networks, which leverages the probability density function of the beta distribution and some contextual factors, to dynamically compute the trust and reputation values of nodes, leading to efficient data dissemination, where malicious nodes are effectively identified and bypassed during that process. Simulation experiments using the ONE simulator show that CATR is superior to the Epidemic protocol, the so-called beta-based trust and reputation evaluation system (denoted BTRES), and the secure and privacy-preserving structure in opportunistic networks (denoted PPHB+), achieving an improvement of 22%, 15%, and 9% in terms of average latency, number of messages dropped, and average hop count, respectively, under varying number of nodes, buffer size, time to live, and message generation interval.
- 15 October 2024
- Published by SAGE Publications in Journal of High Speed Networks
- Vol. 30 (4) , 657-677
Survey on securing wireless networks through a blockchain-based framework
In the contemporary era, blockchain technology has brought about a significant transformation in the realm of digital currency through innovations like Bitcoin. A blockchain serves as a decentralized ledger, ensuring an immutable record of transactions across a network. Recent observations indicate the pivotal role of blockchain technology not only in the financial sector but also in networking. This study considers blockchain as the essential link in establishing a genuinely decentralized, trustless, and secure environment for network nodes. The objective is to provide a systematic and comprehensive overview of futuristic endeavours in this domain. The exploration begins with an examination of the fundamental operational concepts of blockchains and how these systems achieve decentralization, security, and suitability. The focus then shifts towards addressing open research challenges within blockchain technologies, particularly in securing diverse communication networks such as Distributed Computing, Vehicular Ad-hoc Networks, Opportunistic Networks, and Delay Tolerant Networks. Simulation results underscore the superior security performance of blockchain, especially under conditions of attack.
- 15 October 2024
- Published by SAGE Publications in Journal of High Speed Networks
- Vol. 30 (4) , 657-677
Survey on securing wireless networks through a blockchain-based framework
In the contemporary era, blockchain technology has brought about a significant transformation in the realm of digital currency through innovations like Bitcoin. A blockchain serves as a decentralized ledger, ensuring an immutable record of transactions across a network. Recent observations indicate the pivotal role of blockchain technology not only in the financial sector but also in networking. This study considers blockchain as the essential link in establishing a genuinely decentralized, trustless, and secure environment for network nodes. The objective is to provide a systematic and comprehensive overview of futuristic endeavours in this domain. The exploration begins with an examination of the fundamental operational concepts of blockchains and how these systems achieve decentralization, security, and suitability. The focus then shifts towards addressing open research challenges within blockchain technologies, particularly in securing diverse communication networks such as Distributed Computing, Vehicular Ad-hoc Networks, Opportunistic Networks, and Delay Tolerant Networks. Simulation results underscore the superior security performance of blockchain, especially under conditions of attack.