Adaptive defenses for vehicular networks
How can a vehicle distinguish legitimate neighbors from fabricated identities and changing adversarial behavior?
This research brings together dynamic clustering, trust-aware detection, forgetting-aware learning, and cross-temporal analysis to study Sybil attacks and misbehavior in vehicular networks. The central focus is detection reliability as traffic conditions and attacker behavior evolve.
Related publications
7 recordsDynamic K-Means Clustering for Sybil Attack Detection in VANETs
Gideon Adele, Anirudh Paranjothi, Mohammad S. Khan
IEEE 16th Annual Computing and Communication Workshop and Conference (CCWC), 2026, pp. 1444–1450
Sybil Attack Detection in VANETs: A Forgetting-Aware Approach Using Stochastic Gradient Descent with Exponential Weight Decay
Gideon Oluwasegun Adele, Anirudh Paranjothi, Johnson P. Thomas
SSRN preprint, 2026
Explore 5 more related publications
XTVD: Robust Cross-Temporal Misbehavior Detection for Time-Varying Attacks in VANETs
Dilruba Shareen, Anirudh Paranjothi, Mohammad Khan
IEEE 104th Vehicular Technology Conference (VTC2026-Fall), 2026
Rethinking Misbehavior Detection Reliability in VANETs under Reaction-Aware Insider Attacks
Dilruba Shareen, Anirudh Paranjothi
IEEE Global Communications Conference (Globecom), 2026
Trust-Aware Sybil Attack Detection for Resilient Vehicular Communication
Thomas L. Morton, Abinash Borah, Anirudh Paranjothi
Internet Technology Letters, 2025
A Survey and Comparative Analysis of Methods for Countering Sybil Attacks in VANETs
Gideon Adele, Abinash Borah, Anirudh Paranjothi, Mohammad S. Khan
IEEE CCWC, 2024
Trust-Aware Sybil Attack Detection for Resilient Vehicular Communication
Thomas Morton, Abinash Borah, Anirudh Paranjothi
Internet Technology Letters / pre-publication record, 2024