研究图像模型对抗攻击与防御，提升真实场景下模型安全性。
Adversarial Machine Learning: Attacking and Safeguarding Image Datasets
- 用FGSM攻击四大数据集上的CNN模型，验证其脆弱性。
- 通过对抗训练重训模型，使准确率下降从平均60%降至20%以下。
- 适合关注模型安全、对抗样本防御的研究者与工程师。
本文研究卷积神经网络（CNN）在对抗攻击下的脆弱性，并探索防护方法。实验在CIFAR-10、ImageNet、MNIST和Fashion-MNIST四个常用图像数据集上进行，模型达到高基线准确率。采用快速梯度符号法（FGSM）对模型进行攻击，通过微小扰动显著降低模型准确率。为应对该攻击，提出再训练策略：在正常图像与对抗样本混合数据上重新训练模型以增强鲁棒性。再次应用FGSM攻击经过对抗训练的模型，结果显示其准确率下降幅度明显减小，表明防御有效；但仍有部分性能损失，说明仍存在未完全解决的漏洞。研究强调了在现实部署中构建更强防御机制的必要性。
原文摘要 · Abstract (English)
This paper examines the vulnerabilities of convolutional neural networks (CNNs) to adversarial attacks and explores a method for their safeguarding. In this study, CNNs were implemented on four of the most common image datasets, namely CIFAR-10, ImageNet, MNIST, and Fashion-MNIST, and achieved high baseline accuracy. To assess the strength of these models, the Fast Gradient Sign Method was used, which is a type of exploit on the model that is used to bring down the models accuracies by adding a very minimal perturbation to the input image. To counter the FGSM attack, a safeguarding approach went through, which includes retraining the models on clear and pollutant or adversarial images to increase their resistance ability. The next step involves applying FGSM again, but this time to the adversarially trained models, to see how much the accuracy of the models has gone down and evaluate the effectiveness of the defense. It appears that while most level of robustness is achieved against the models after adversarial training, there are still a few losses in the performance of these models against adversarial perturbations. This work emphasizes the need to create better defenses for models deployed in real-world scenarios against adversaries.
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。