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 1909.04288cs.LGstat.ML
收藏

BOSH:一种有效的基于决策攻击的Meta算法

BOSH: An Efficient Meta Algorithm for Decision-based Attacks

Zhejiang University(浙江大学);University of California, Davis(加州大学戴维斯分校);University of California, Los Angeles(加州大学洛杉矶分校)

Zhenxin Xiao, Puyudi Yang, Yuchen Jiang, Kai-Wei Chang, Cho-Jui Hsieh

摘要:

对抗性示例生成成为评价机器学习模型鲁棒性的一种可行方法。在本文中,我们考虑硬标签黑盒攻击(又名基于决策的攻击),这是一个具有挑战性的设置,仅基于一系列黑盒硬标签查询生成对抗性示例。这种类型的攻击可用于攻击离散和复杂的模型,例如梯度提升决策树(GBDT)和基于检测的防御模型。现有的基于迭代局部更新的基于决策的攻击往往会陷入局部最小值,无法生成失真最小的最佳对抗样本。为了解决这个问题,我们提出了一个有效的Meta算法称为BOSH攻击,极大地改善了现有的算法,通过贝叶斯优化(BO)和连续减半(SH)。特别是,在搜索对抗性示例时,我们不是遍历单个解决方案路径,而是维护一个解决方案路径池来探索重要区域。我们的经验表明,该算法收敛到一个更好的解决方案比现有的方法,而查询计数小于应用多个随机初始化的一个因素为10。

英文摘要:

Adversarial example generation becomes a viable method for evaluating the robustness of a machine learning model. In this paper, we consider hard-label black-box attacks (a.k.a. decision-based attacks), which is a challenging setting that generates adversarial examples based on only a series of black-box hard-label queries. This type of attacks can be used to attack discrete and complex models, such as Gradient Boosting Decision Tree (GBDT) and detection-based defense models. Existing decision-based attacks based on iterative local updates often get stuck in a local minimum and fail to generate the optimal adversarial example with the smallest distortion. To remedy this issue, we propose an efficient meta algorithm called BOSH-attack, which tremendously improves existing algorithms through Bayesian Optimization (BO) and Successive Halving (SH). In particular, instead of traversing a single solution path when searching an adversarial example, we maintain a pool of solution paths to explore important regions. We show empirically that the proposed algorithm converges to a better solution than existing approaches, while the query count is smaller than applying multiple random initializations by a factor of 10.

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。

↑