Robust and Safe Traffic Sign Recognition using N-version with Weighted Voting

2025/07/09 by Linyun Gao, Gao, Linyun, Qiang Wen +3
Computer Science · Engineering · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Autonomous Vehicle Technology and Safety #FOS: Computer and information sciences #Machine Learning (cs.LG) #Software Engineering (cs.SE)

paper · pdf · doi:10.48550/arxiv.2507.06907

openalex publication_date 2025/07/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Towards Safety-Aware Computing System Design in Autonomous Vehicles
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Practical Black-Box Attacks against Machine Learning
• Explaining and Harnessing Adversarial Examples
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• ImageNet classification with deep convolutional neural networks

Related

• Redesigning Traffic Signs to Mitigate Machine-Learning Patch Attacks
• Evaluating the Impact of Adversarial Attacks on Traffic Sign Classification using the LISA Dataset
• A Hybrid Defense Method against Adversarial Attacks on Traffic Sign Classifiers in Autonomous Vehicles
• VISAT: Benchmarking Adversarial and Distribution Shift Robustness in Traffic Sign Recognition with Visual Attributes
• Adversary ML Resilience in Autonomous Driving Through Human Centered Perception Mechanisms