Revisiting DeepFool: generalization and improvement
This work addresses the need for more efficient and accurate robustness evaluation methods in adversarial machine learning, though it appears incremental as it builds upon the established DeepFool approach.
The paper tackles the problem of evaluating robustness to minimal L2 adversarial perturbations in deep neural networks by introducing a new family of attacks that generalize DeepFool, achieving better effectiveness and computational efficiency than existing methods.
Deep neural networks have been known to be vulnerable to adversarial examples, which are inputs that are modified slightly to fool the network into making incorrect predictions. This has led to a significant amount of research on evaluating the robustness of these networks against such perturbations. One particularly important robustness metric is the robustness to minimal $\ell_2$ adversarial perturbations. However, existing methods for evaluating this robustness metric are either computationally expensive or not very accurate. In this paper, we introduce a new family of adversarial attacks that strike a balance between effectiveness and computational efficiency. Our proposed attacks are generalizations of the well-known DeepFool (DF) attack, while they remain simple to understand and implement. We demonstrate that our attacks outperform existing methods in terms of both effectiveness and computational efficiency. Our proposed attacks are also suitable for evaluating the robustness of large models and can be used to perform adversarial training (AT) to achieve state-of-the-art robustness to minimal $\ell_2$ adversarial perturbations.