Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack
This provides a more feasible and reliable method for practitioners with limited resources to evaluate adversarial robustness, though it is incremental as it builds on existing evaluation paradigms.
The paper tackles the high computational cost of AutoAttack for evaluating adversarial robustness by proposing the minimum-margin attack, which achieves comparable performance while reducing computational time to 3% of AutoAttack's cost.
The AutoAttack (AA) has been the most reliable method to evaluate adversarial robustness when considerable computational resources are available. However, the high computational cost (e.g., 100 times more than that of the project gradient descent attack) makes AA infeasible for practitioners with limited computational resources, and also hinders applications of AA in the adversarial training (AT). In this paper, we propose a novel method, minimum-margin (MM) attack, to fast and reliably evaluate adversarial robustness. Compared with AA, our method achieves comparable performance but only costs 3% of the computational time in extensive experiments. The reliability of our method lies in that we evaluate the quality of adversarial examples using the margin between two targets that can precisely identify the most adversarial example. The computational efficiency of our method lies in an effective Sequential TArget Ranking Selection (STARS) method, ensuring that the cost of the MM attack is independent of the number of classes. The MM attack opens a new way for evaluating adversarial robustness and provides a feasible and reliable way to generate high-quality adversarial examples in AT.