Evaluating the Impact of Adversarial Attacks on Traffic Sign Classification using the LISA Dataset

2025/09/08 by Nabeyou Tadessa, Tadessa, Nabeyou, Balaji Iyangar +3
Computer Science · #Adversarial Robustness in Machine Learning #Adversarial system #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Convolutional neural network #Digital Media Forensic Detection #FOS: Computer and information sciences #Gradient descent #MNIST database #Robustness (evolution) #Traffic sign #Traffic sign recognition

paper · pdf · doi:10.48550/arxiv.2509.06835

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/09/08 · openalex created_date 2025/10/11 · openalex updated_date 2026/08/05

Abstract

Adversarial attacks pose significant threats to machine learning models by introducing carefully crafted perturbations that cause misclassification. While prior work has primarily focused on MNIST and similar datasets, this paper investigates the vulnerability of traffic sign classifiers using the LISA Traffic Sign dataset. We train a convolutional neural network to classify 47 different traffic signs and evaluate its robustness against Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks. Our results show a sharp decline in classification accuracy as the perturbation magnitude increases, highlighting the models susceptibility to adversarial examples. This study lays the groundwork for future exploration into defense mechanisms tailored for real-world traffic sign recognition systems.

Citations

• Certified Adversarial Robustness via Randomized Smoothing
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Adam: A Method for Stochastic Optimization
• Intriguing properties of neural networks
• Visualizing and Understanding Convolutional Networks
• ImageNet classification with deep convolutional neural networks
• Gradient-based learning applied to document recognition

Related

• Evaluating Adversarial Attacks on Traffic Sign Classifiers beyond Standard Baselines
• Adversarial Attacks on Traffic Sign Recognition: A Survey
• Snowball Adversarial Attack on Traffic Sign Classification
• VISAT: Benchmarking Adversarial and Distribution Shift Robustness in Traffic Sign Recognition with Visual Attributes
• Securing Traffic Sign Recognition Systems in Autonomous Vehicles