测试对抗攻击对交通标志识别模型的破坏力，发现小扰动就让准确率暴跌。
Evaluating the Impact of Adversarial Attacks on Traffic Sign Classification using the LISA Dataset
- 用卷积神经网络训练47类交通标志分类器，测试对抗攻击效果。
- 扰动幅度增大时，分类准确率急剧下降，模型极脆弱。
- 研究结果为真实场景交通识别系统防御提供基础参考。
对抗攻击通过精心设计的微小扰动导致机器学习模型误分类，构成严重威胁。尽管以往研究多集中于MNIST等数据集，本文首次基于LISA Traffic Sign数据集，评估交通标志分类器在对抗攻击下的脆弱性。我们训练了一个卷积神经网络以识别47类不同交通标志，并在该模型上测试Fast Gradient Sign Method (FGSM) 和 Projected Gradient Descent (PGD) 攻击的性能。实验结果显示，随着扰动幅度增加，分类准确率显著下降，暴露出模型对对抗样本的高度敏感性。本研究为未来面向真实世界交通标志识别系统的防御机制探索奠定了基础。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。