arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.01809cs.LGcs.AI
收藏

通过分层生成网络提高目标对抗示例的可迁移性

Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks

RealAI(瑞莱智慧);Peng Cheng Laboratory(鹏城实验室);Pazhou Laboratory(琶洲实验室);Tsinghua University(清华大学);Sea AI Lab(Sea人工智能实验室)

Xiao Yang, Yinpeng Dong, Tianyu Pang, Hang Su, Jun Zhu

摘要:

基于转移的对抗攻击可以在黑盒环境下评估模型的鲁棒性。几种方法已经证明了令人印象深刻的非靶向可转移性,然而,有效地产生靶向可转移性仍然具有挑战性。为此,我们开发了一个简单而有效的框架,应用分层生成网络来制作有针对性的基于转移的对抗性示例。特别是,我们有助于摊销的设计,以及适应多类有针对性的攻击。在ImageNet上进行的大量实验表明,我们的方法比现有方法显著提高了针对性黑盒攻击的成功率-它仅基于一个替代白盒模型对六个不同模型的平均成功率达到29.1%,这明显优于最先进的基于梯度的攻击方法。此外,所提出的方法也是更有效的超过一个数量级比基于梯度的方法。

英文摘要:

Transfer-based adversarial attacks can evaluate model robustness in the black-box setting. Several methods have demonstrated impressive untargeted transferability, however, it is still challenging to efficiently produce targeted transferability. To this end, we develop a simple yet effective framework to craft targeted transfer-based adversarial examples, applying a hierarchical generative network. In particular, we contribute to amortized designs that well adapt to multi-class targeted attacks. Extensive experiments on ImageNet show that our method improves the success rates of targeted black-box attacks by a significant margin over the existing methods -- it reaches an average success rate of 29.1\% against six diverse models based only on one substitute white-box model, which significantly outperforms the state-of-the-art gradient-based attack methods. Moreover, the proposed method is also more efficient beyond an order of magnitude than gradient-based methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑