arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.12792cs.LGcs.AIstat.ML
收藏

RayS:一种硬标记对抗攻击的射线搜索方法

RayS: A Ray Searching Method for Hard-label Adversarial Attack

University of California, Los Angeles(加州大学洛杉矶分校)

Jinghui Chen, Quanquan Gu

摘要:

深度神经网络容易受到对抗攻击的攻击。在不同的攻击设置中,最具挑战性但最实用的是硬标签设置,其中攻击者只能访问目标模型的硬标签输出(预测标签)。在广泛使用的$L_\infty$范数威胁模型下,以前的尝试在攻击成功率方面不够有效,在查询复杂度方面也不够有效。本文提出了射线搜索攻击(RayS),它大大提高了硬标签攻击的有效性和效率。与以前的作品不同,我们重新制定的连续问题,找到最接近的决策边界到一个离散的问题,不需要任何零阶梯度估计。同时,通过快速检查步骤消除所有不必要的搜索。这大大减少了硬标签攻击所需的查询数量。此外,有趣的是,我们发现所提出的RayS攻击也可以用作可能的“虚假鲁棒”模型的健全性检查。在最近提出的几种声称达到最先进的鲁棒准确性的防御方法上,我们的攻击方法表明,当前的白盒/黑盒攻击仍然可以提供虚假的安全感,并且最流行的PGD攻击和RayS攻击之间的鲁棒准确性下降可能与$28\%$一样大。我们相信,我们提出的RayS攻击可以帮助识别错误的鲁棒模型,击败大多数白盒/黑盒攻击。

英文摘要:

Deep neural networks are vulnerable to adversarial attacks. Among different attack settings, the most challenging yet the most practical one is the hard-label setting where the attacker only has access to the hard-label output (prediction label) of the target model. Previous attempts are neither effective enough in terms of attack success rate nor efficient enough in terms of query complexity under the widely used $L_\infty$ norm threat model. In this paper, we present the Ray Searching attack (RayS), which greatly improves the hard-label attack effectiveness as well as efficiency. Unlike previous works, we reformulate the continuous problem of finding the closest decision boundary into a discrete problem that does not require any zeroth-order gradient estimation. In the meantime, all unnecessary searches are eliminated via a fast check step. This significantly reduces the number of queries needed for our hard-label attack. Moreover, interestingly, we found that the proposed RayS attack can also be used as a sanity check for possible "falsely robust" models. On several recently proposed defenses that claim to achieve the state-of-the-art robust accuracy, our attack method demonstrates that the current white-box/black-box attacks could still give a false sense of security and the robust accuracy drop between the most popular PGD attack and RayS attack could be as large as $28\%$. We believe that our proposed RayS attack could help identify falsely robust models that beat most white-box/black-box attacks.

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。

↑