PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks

Authors: Ping Guo, Zhiyuan Yang, Xi Lin, Qingchuan Zhao, Qingfu Zhang
Published: 2024-01-19

Source: https://arxiv.org/abs/2401.10586

PDF: https://arxiv.org/pdf/2401.10586

Labels Predicted by AI

防御手法 ウォーターマーキング 敵対的攻撃

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

Black-box query-based attacks constitute significant threats to Machine Learning as a Service (MLaaS) systems since they can generate adversarial examples without accessing the target model’s architecture and parameters. Traditional defense mechanisms, such as adversarial training, gradient masking, and input transformations, either impose substantial computational costs or compromise the test accuracy of non-adversarial inputs. To address these challenges, we propose an efficient defense mechanism, PuriDefense, that employs random patch-wise purifications with an ensemble of lightweight purification models at a low level of inference cost. These models leverage the local implicit function and rebuild the natural image manifold. Our theoretical analysis suggests that this approach slows down the convergence of query-based attacks by incorporating randomness into purifications. Extensive experiments on CIFAR-10 and ImageNet validate the effectiveness of our proposed purifier-based defense mechanism, demonstrating significant improvements in robustness against query-based attacks.