University Events

Description: Topic: Admire: Artificial Intelligence Approach to Detect Misbehavior and Invoke Revocation in Vehicular Environment

Location: Lester W. Cory Conference Room, Science & Engineering Building (SENG), Room 213A

Abstract:
Autonomous Vehicle Technology (AVT) offers fundamental restructure of the transportation. Connected Vehicles Technology (CVT) further enhances Intelligent Transportation Systems (ITS). Despite the maturity of the technology, the deployment in the real-world standstills partially due to security concerns. IEEE 1609.2 provides security mechanisms by defining secure message formats and procedures. Traditional approaches such as public key infrastructure (PKI) are insufficient due to the rapid dynamics and privacy requirements of Vehicular Ad-Hoc Networks (VANET). By injecting malware to VANET devices or by stealing certificates an attacker can fabricate application or management messages, compromising the security provided with IEEE 1609.2. Solutions to secure backend in vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications include Security Credential Management System (SCMS). It supports certificate provision with privacy preservation and operation efficiency as PKI for Vehicle Networks or "Vehicular PKI".

However, timely misbehavior detection and certificate revocation remain an open problem. This work aims at enhancing privacy-preserving credential management with efficiency for SCMS. It utilizes context-adaptive machine learning technique to detect misbehaviors and revoke certificates and cast them out of the system to secure V2X communications. This approach works in two phases at three levels: Phase 1: Revelation to detect misbehavior while preserving privacy and Phase 2: Reaction to revoke certificates for credential management. Revelation phase reveals misbehaving vehicles on the local and cooperative levels. It emulates human logic in shaping mistrust before ending a relation, using the toolset, called Context Adaptive Machine Learning Tool (CAMLeT), to be developed. Revocation is done on three different levels; Local, Cooperative and Regional, each applying CAMLeT to perform a fact-analysis on misbehavior detection.

The work contributes to privacy-preserved security credential management with efficiency. Its novelty lies at timely misbehavior detection and revocation for the vehicular environment. By applying artificial intelligence using CAMLeT, data centric analysis accelerates misbehavior detection. Granting local autonomous instead of the global decision, scalability of credential management is achieved. The work presents an autonomous driving framework where vehicles cooperate with each other to seek safe and secure driving.

Note: All ECE Graduate Students are ENCOURAGED to attend.
All interested parties are invited to attend. Open to the public.

Advisor: Dr. Hong Liu
Committee Members: Dr. Paul J. Fortier, Dr. Honggang Wang, Department of Electrical & Computer Engineering, UMass Dartmouth; Dr. Jonathan Petit, Senior Director of Research, OnBoard Security; Dr. Kavitha Chandra, Department of Electrical & Computer Engineering, UMass Lowell

*For further information, please contact Dr. Hong Liu at 508.999.8514, or via email at hliu@umassd.edu.