Robust and Safe Traffic Sign Recognition using N-version with Weighted Voting
This work addresses safety-critical challenges in autonomous driving by enhancing traffic sign recognition against adversarial attacks, though it is incremental as it builds on ensemble methods and safety analysis.
The paper tackles the vulnerability of traffic sign recognition in autonomous vehicles to adversarial attacks by proposing an N-version machine learning framework with a safety-aware weighted voting mechanism, demonstrating significant robustness improvements under adversarial conditions.
Autonomous driving is rapidly advancing as a key application of machine learning, yet ensuring the safety of these systems remains a critical challenge. Traffic sign recognition, an essential component of autonomous vehicles, is particularly vulnerable to adversarial attacks that can compromise driving safety. In this paper, we propose an N-version machine learning (NVML) framework that integrates a safety-aware weighted soft voting mechanism. Our approach utilizes Failure Mode and Effects Analysis (FMEA) to assess potential safety risks and assign dynamic, safety-aware weights to the ensemble outputs. We evaluate the robustness of three-version NVML systems employing various voting mechanisms against adversarial samples generated using the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks. Experimental results demonstrate that our NVML approach significantly enhances the robustness and safety of traffic sign recognition systems under adversarial conditions.