Citation

Chaudhary, Alka and Yogarayan, Sumendra and Sharma, Vandana (2026) Hybrid Explainable AI Models for Accurate and Transparent Intrusion Detection in VANETs. In: 2026 International Conference on Connected Intelligence for Industrial Applications, CI2A 2026, 3 April 2026 - 5 April 2026, Punjab.

Text 16.pdf - Published Version Restricted to Repository staff only Download (232kB)

Abstract

Vehicular Ad-hoc Networks (VANETs) enable communication infrastructures for Intelligent Transportation Systems (ITS), enabling vehicle-2-vehicle (V2V) cooperation, enhanced road safety and eCiciency (e.g. in traCic management) through V2V, V2I and V2X communications. With more interconnection of VANET infrastructures, they are vulnerable to cyberattacks including spoofing, Sybil attacks, false data injection, jamming and others distributed denial of service (DDoS), which may harm the security and credibility of roads. Deep learning-based intrusion detection systems based on machine learning have has shown a significant level of performance in detecting these complicated intrusions, but their black-box nature restricts interpretability, transparency and regulatory fit. Xplainable Artificial Intelligence (XAI) has been one of the crucial facilitators to improve the creditworthiness and transparency of AI-controlled IDS systems. This review examines available hybrid XAI-based IDS methods that integrate learning models of explainability mechanisms in order to enhance detection accuracy as well as interpretability in VANETs. This paper draw up the existing tendencies in the field of methodology, their advantages and restrictions, and finds vital gaps in research. Lastly, directions are in the future suggested to reach the objective of complete transparency, trustworthiness, and verifiability of the solutions of the next generation vehicular network IDS.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	VANETs, Intrusion Detection System
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	04 Aug 2026 07:00
Last Modified:	04 Aug 2026 07:00
URII:	http://shdl.mmu.edu.my/id/eprint/16497

Downloads

Edit (login required)