Saif Eddin Jabari

A Trigger Exploration Method for Backdoor Attacks on Deep Learning-Based Traffic Control Systems

2021 · 2021 60th IEEE Conference on Decision and Control (CDC)

Deep learning methods are in the forefront of techniques used to perform complex controls in autonomous vehicles (AVs). Such methods are vulnerable to nuanced types of adversarial attacks, and can have sever safety implications. Specifically, …

Optimal Smoothing Distribution Exploration for Backdoor Neutralization in Deep Learning-based Traffic Systems

2023 · arXiv (Cornell University)

Deep Reinforcement Learning (DRL) enhances the efficiency of Autonomous Vehicles (AV), but also makes them susceptible to backdoor attacks that can result in traffic congestion or collisions. Backdoor functionality is typically incorporated by contaminating training …