Focus on Generalization: Improving Adversarial Transferability via Bi-Level Bias Mitigation

摘要

Transfer-based adversarial attacks have endowed adversarial examples with the ability to transfer from a source model to an unknown target model, which poses a more realistic threat to security-critical applications. Existing transferable adversarial attacks generally suffer from overfitting to the source model, i.e., the perturbations are locally optimal in the source model and focus on the model-specific information. We demand the adversarial perturbation to contain more generalized knowledge, which reveals the intrinsic general properties and can introduce model-general optimum into adversarial examples, for improving transferability. To this end, we devise a Bi-level Bias Mitigated Attack (BBMA), which empowers the transferability of adversarial examples by exploring generalization in two levels: 1) Progressive filtering of high-frequency sample components. We first propose to remove the sample-specific high-frequency components of samples to explore model-level generation. To simulate how a model evaluates feature importance at different stages, we devise a stride-wise step-tuning strategy to progressively produce multiple samples for aggregating the gradients. 2) Accumulated gradient-guided model attention shift. To facilitate the sample-level bias mitigation, we employ an accumulated gradient-guided attention map to distort the more generalized features during perturbation generation. Comprehensive experiments on several benchmarks demonstrate the superiority of our method in attack transferability over state-of-the-art attacks.