Academic Profile

Dr. Jagdeep Singh (SM IEEE) is an Assistant Professor in the Department of Computer Science and Engineering at Sant Longowal Institute of Engineering and Technology (SLIET), Longowal. He earned his Ph.D. in Computer Engineering from the University of Delhi. His research interests span Artificial Intelligence, Machine Learning, Delay-Tolerant Networks, and Cybersecurity. He is an AICTE-certified Master Trainer in High-Performance Computing and has published extensively in reputed journals such as IEEE Internet of Things, Journal of Ambient Intelligence and Humanized Computing, IET, and the International Journal of Communication Systems. He has also presented his work at several flagship international conferences, including IEEE ICC, IEEE Globecom, AINA, and IEEE CITS. Dr. Singh is a Senior Member of IEEE and INAE, and a member of the International Association of Engineers. He actively contributes to the research community through technical program committees and reviews for top-tier journals like IEEE IoT, IEEE TIFS, IEEE Access, and Wiley journals. He has organized multiple academic programs and has also received funding from AICTE for conducting advanced-level FDPs and short-term training programs. He is a recipient of the Shastri Conference and Lecture Series Grant (2021–22) and led Team EMMET to victory in the Prototype and Ideation Stages of the Indian Web Browser Development Challenge by MeitY, securing ₹12,00,000. He was selected as a young faculty presenter in the AI theme at ESTIC 2025, organized by DST, Government of India, at Bharat Mandapam. He has delivered numerous expert lectures on cybersecurity and AI-based technologies in various national programs.

Editorial Roles

No Editorial Roles

This user currently does not serve as an editor for any ICCK journals.

ICCK Publications

Total Publications: 1
Open Access | Research Article | 07 February 2026
A Novel System for Detecting Model Poisoning Attacks in Federated Learning
Journal of Reliable and Secure Computing | Volume 2, Issue 1: 27-38, 2026 | DOI: 10.62762/JRSC.2025.385825
Abstract
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 sy... More >

Graphical Abstract
A Novel System for Detecting Model Poisoning Attacks in Federated Learning