Swaminathan Kalyanaraman
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Swaminathan Kalyanaraman has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Sivaram Ponnusamy
Sandip University, Nashik, India
11 shared publications - R. Karthikeyan
University of College of Engineering, Thanjavur, India
10 shared publications - R. Kiruba Buri
Department of CSE, School of Computing, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai, India
8 shared publications - Harish Ravali Kasiviswanathan
University College of Engineering, Pattukkottai, India
6 shared publications - A. Arivazhagi
SRM Institute of Science and Technology
3 shared publications K. Sankar
3 shared publications
Latest Publications
- 10 July 2026
- Published by IGI Global Scientific Publishing
- p. 125-150
Edge Computing-Empowered Federated Learning for Decentralized Intrusion Detection Using Autoencoders
The dramatic increase of IOT devices and decentralized networks has aggravated the potential entry points of cyber threats, resulting in a demand for efficient Intrusion Detection Systems (IDS). Centrally controlled traditional models of learning are affected by issues of latency, limits of the bandwidth, and privacy leakage. To address these problems, the present work put forward a Local Computing Enhanced Federated Learning (EC-FL) framework combined with Autoencoder-based Machine Learning models to achieve on-the-fly intrusion detection. The proposed schema spreads out model training across the edge devices, thus allowing collaborative learning without the need of sharing raw data. Comparing cloud-based IDS, the experiments conducted on standard datasets like NSL-KDD and CICIDS2017 depict a better detection rate (96.7%), lower training time (31%), and lesser communication overhead. The method proposed is instrumental in augmenting scalability, ensuring data privacy, and enhancing the real-time anomaly detection in the interconnected world of IoT network infrastructures.
- 10 July 2026
- Published by IGI Global Scientific Publishing
- p. 125-150
Edge Computing-Empowered Federated Learning for Decentralized Intrusion Detection Using Autoencoders
The dramatic increase of IOT devices and decentralized networks has aggravated the potential entry points of cyber threats, resulting in a demand for efficient Intrusion Detection Systems (IDS). Centrally controlled traditional models of learning are affected by issues of latency, limits of the bandwidth, and privacy leakage. To address these problems, the present work put forward a Local Computing Enhanced Federated Learning (EC-FL) framework combined with Autoencoder-based Machine Learning models to achieve on-the-fly intrusion detection. The proposed schema spreads out model training across the edge devices, thus allowing collaborative learning without the need of sharing raw data. Comparing cloud-based IDS, the experiments conducted on standard datasets like NSL-KDD and CICIDS2017 depict a better detection rate (96.7%), lower training time (31%), and lesser communication overhead. The method proposed is instrumental in augmenting scalability, ensuring data privacy, and enhancing the real-time anomaly detection in the interconnected world of IoT network infrastructures.
- 2 July 2026
- Published by Springer Nature
- p. 13-23
Support Vector Machine-Lyapunov Control for Nonlinear Cluster Synchronization
- 2 July 2026
- Published by Springer Nature
- p. 13-23
Support Vector Machine-Lyapunov Control for Nonlinear Cluster Synchronization
- 1 May 2026
- Published by Springer Nature
- p. 201-213
Strengthening of Cyber-Physical Infrastructure Resilience by DRL Adaptive Resource Management
- 1 May 2026
- Published by Springer Nature
- p. 201-213
Strengthening of Cyber-Physical Infrastructure Resilience by DRL Adaptive Resource Management
- 3 April 2026
- Published by IGI Global Scientific Publishing
- p. 1-16
Adaptive Adversarial-Resilient Explainable Intrusion Detection System for 6G Edge Networks (AARE-IDS)
The rapid progression towards sixth-generation (6G) edge-intelligent networks requires Intrusion Detection Systems (IDS) that are interpretable, lightweight, and resilient to adversarial maneuvering. Current deep learning-based IDS systems, including CiNeT, present misleading accuracy through many negative factors. Using the CiNeT framework as the foundation of this paper introduces AARE-IDS, Adaptive Adversarially Resilient Explainable Intrusion Detection System (IDS), for real-time 6G edge settings. AARE-IDS system is particularly exceptional amongst similar developments due to its lightweight bijective traffic encoding (NeT2I-Lite), hybrid CNN - Transformer detector, adversarially trained resilience layer, utilizing a federated learning framework to investigate model aggregation and derived from a differential privacy standard for added security while sharing models. Through extensive experiments on the ToN-IoT, UNSW-NB15, and CICIDS-2018 datasets, AARE-IDS achieved 98.9% accuracy, 39% better robustness against FGSM/PGD attacks, and 45% less CPU overhead compared to CiNeT.
- 3 April 2026
- Published by IGI Global Scientific Publishing
- p. 1-16
Adaptive Adversarial-Resilient Explainable Intrusion Detection System for 6G Edge Networks (AARE-IDS)
The rapid progression towards sixth-generation (6G) edge-intelligent networks requires Intrusion Detection Systems (IDS) that are interpretable, lightweight, and resilient to adversarial maneuvering. Current deep learning-based IDS systems, including CiNeT, present misleading accuracy through many negative factors. Using the CiNeT framework as the foundation of this paper introduces AARE-IDS, Adaptive Adversarially Resilient Explainable Intrusion Detection System (IDS), for real-time 6G edge settings. AARE-IDS system is particularly exceptional amongst similar developments due to its lightweight bijective traffic encoding (NeT2I-Lite), hybrid CNN - Transformer detector, adversarially trained resilience layer, utilizing a federated learning framework to investigate model aggregation and derived from a differential privacy standard for added security while sharing models. Through extensive experiments on the ToN-IoT, UNSW-NB15, and CICIDS-2018 datasets, AARE-IDS achieved 98.9% accuracy, 39% better robustness against FGSM/PGD attacks, and 45% less CPU overhead compared to CiNeT.
- 1 April 2026
- Published by Springer Nature
- p. 248-259
Adaptive Intelligent Routing Algorithm for Integrating MANETs with IoT Networks
- 1 April 2026
- Published by Springer Nature
- p. 248-259
Adaptive Intelligent Routing Algorithm for Integrating MANETs with IoT Networks
- 8 February 2026
- Published by Springer Nature
- p. 65-77
Optimizing Intrusion Detection Pipelines with AutoML: XGBoost for Enhanced Security
- 8 February 2026
- Published by Springer Nature
- p. 65-77
Optimizing Intrusion Detection Pipelines with AutoML: XGBoost for Enhanced Security
- 2 January 2026
- Published by Springer Nature
- p. 53-64
IoT-Driven Predictive Analytics for Smart Agriculture Using Random Forest Algorithm
- 2 January 2026
- Published by Springer Nature
- p. 53-64
IoT-Driven Predictive Analytics for Smart Agriculture Using Random Forest Algorithm
- 14 November 2025
- Published by IGI Global Scientific Publishing
- p. 269-298
Block Chain-Reliable Incentive Cooperation System for Multiple Ways of Hopping Wireless Type of Network Infrastructure
In Multiple way of hopping Wireless type of Networks infrastructure, (MWN), mobile nodal points often relay packets through cooperative nodes. However, selfish node behavior has a count of detrimental effects on node cooperation and network performance, reducing node connectivity, throughput, and power consumption. In this proposed ‘Block Chain based Reliable Incentive Cooperation System Infrastructure,' for secure cooperation among trusted nodal points and to thwart the selfishness attack, collision attack and Denial of ser-vice attacks. To discourage selfish node behavior, we use incentive mechanisms that charge nodal points efficiently. The block chain operation is used to create more secure communica-tion between nodes, hence improving integrity and secrecy. The token-based cheque submission technique is used to reduce collusion attacks. The Accounting Center (AC) efficiently updates and stores the nodes' credits, classifying the cheques and confirming the nodes' certifications during the eviction process.
- 14 November 2025
- Published by IGI Global Scientific Publishing
- p. 269-298
Block Chain-Reliable Incentive Cooperation System for Multiple Ways of Hopping Wireless Type of Network Infrastructure
In Multiple way of hopping Wireless type of Networks infrastructure, (MWN), mobile nodal points often relay packets through cooperative nodes. However, selfish node behavior has a count of detrimental effects on node cooperation and network performance, reducing node connectivity, throughput, and power consumption. In this proposed ‘Block Chain based Reliable Incentive Cooperation System Infrastructure,' for secure cooperation among trusted nodal points and to thwart the selfishness attack, collision attack and Denial of ser-vice attacks. To discourage selfish node behavior, we use incentive mechanisms that charge nodal points efficiently. The block chain operation is used to create more secure communica-tion between nodes, hence improving integrity and secrecy. The token-based cheque submission technique is used to reduce collusion attacks. The Accounting Center (AC) efficiently updates and stores the nodes' credits, classifying the cheques and confirming the nodes' certifications during the eviction process.
- 2 May 2025
- Published by IGI Global Scientific Publishing
- p. 219-232
Federated LSTM Framework for Distributed Traffic Forecasting and Mobility Optimization in Blockchain-Integrated VANETs
This study presents a Federated LSTM framework designed to improve traffic forecasting and mobility optimization in blockchain-integrated Vehicular Ad Hoc Networks (VANETs). By leveraging a federated learning approach, the framework enables collaborative model training across decentralized nodes without requiring direct data sharing, enhancing privacy and data security among network participants. The LSTM model effectively captures temporal traffic patterns, providing accurate and real-time forecasting to support dynamic mobility management. The integration of blockchain ensures data integrity and facilitates secure, transparent communication between vehicles and infrastructure within the VANET. This decentralized approach addresses the challenges of data privacy, system scalability, and efficient resource utilization in traffic prediction and mobility control. The proposed framework holds promise for advancing smart transportation systems by reducing congestion, improving traffic flow, and enhancing the overall efficiency of urban mobility
- 2 May 2025
- Published by IGI Global Scientific Publishing
- p. 219-232
Federated LSTM Framework for Distributed Traffic Forecasting and Mobility Optimization in Blockchain-Integrated VANETs
This study presents a Federated LSTM framework designed to improve traffic forecasting and mobility optimization in blockchain-integrated Vehicular Ad Hoc Networks (VANETs). By leveraging a federated learning approach, the framework enables collaborative model training across decentralized nodes without requiring direct data sharing, enhancing privacy and data security among network participants. The LSTM model effectively captures temporal traffic patterns, providing accurate and real-time forecasting to support dynamic mobility management. The integration of blockchain ensures data integrity and facilitates secure, transparent communication between vehicles and infrastructure within the VANET. This decentralized approach addresses the challenges of data privacy, system scalability, and efficient resource utilization in traffic prediction and mobility control. The proposed framework holds promise for advancing smart transportation systems by reducing congestion, improving traffic flow, and enhancing the overall efficiency of urban mobility
- 24 April 2025
- Published by IGI Global Scientific Publishing
- p. 271-288
Dynamic Resource Allocation in VANETs for Urban Mobility Applications Using Blockchain and Convolutional Neural Networks (CNNs)
Research explores a dynamic resource allocation framework for Vehicular Ad Hoc Networks (VANETs) aimed at optimizing urban mobility applications through the integration of blockchain technology and Convolutional Neural Networks (CNNs). As urban environments face increasing transportation demands, efficient resource allocation in VANETs is essential to support reliable data transmission, reduce congestion, and enhance overall traffic management. The proposed approach leverages blockchain to establish secure, decentralized communication among vehicles, ensuring data integrity and preventing unauthorized access in the highly dynamic network. CNNs are employed to analyze traffic patterns and vehicular movement, extracting valuable insights from vast amounts of real-time data to make informed resource allocation decisions.
- 24 April 2025
- Published by IGI Global Scientific Publishing
- p. 271-288
Dynamic Resource Allocation in VANETs for Urban Mobility Applications Using Blockchain and Convolutional Neural Networks (CNNs)
Research explores a dynamic resource allocation framework for Vehicular Ad Hoc Networks (VANETs) aimed at optimizing urban mobility applications through the integration of blockchain technology and Convolutional Neural Networks (CNNs). As urban environments face increasing transportation demands, efficient resource allocation in VANETs is essential to support reliable data transmission, reduce congestion, and enhance overall traffic management. The proposed approach leverages blockchain to establish secure, decentralized communication among vehicles, ensuring data integrity and preventing unauthorized access in the highly dynamic network. CNNs are employed to analyze traffic patterns and vehicular movement, extracting valuable insights from vast amounts of real-time data to make informed resource allocation decisions.