arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.02189cs.LGstat.ML
收藏

高斯混合模型在$\ell_0$攻击下的鲁棒分类

Robust Classification Under $\ell_0$ Attack for the Gaussian Mixture Model

University of Pennsylvania(宾夕法尼亚大学);University of California, Santa Barbara(加利福尼亚大学圣巴巴拉分校)

Payam Delgosha, Hamed Hassani, Ramtin Pedarsani

摘要:

众所周知,机器学习模型容易受到小但巧妙设计的对抗性扰动的影响,这些扰动可能导致错误分类。虽然在设计各种对抗性环境的攻击和防御方面取得了重大进展,但许多基本和理论问题尚未解决。在本文中,我们考虑的分类存在$\ell_0$ -有界对抗扰动,又名。稀疏的攻击。该设置与其他$\ell_p$ -对抗设置(使用$p\geq 1$)显著不同,因为$\ell_0$ -球是非凸的且高度不平滑。假设数据是根据高斯混合模型分布的,我们的目标是表征最佳的鲁棒分类器和相应的鲁棒分类错误,以及各种鲁棒性,准确性和对手的预算之间的权衡。为此,我们开发了一种名为FilTrun的新型分类算法,它有两个主要模块:过滤和截断。我们的方法的关键思想是首先过滤掉输入的非鲁棒坐标,然后应用精心设计的截断内积进行分类。通过分析FilTrun的性能,我们推导出最优鲁棒分类误差的上界。我们还通过设计一个特定的对抗策略找到了一个下界,该策略使我们能够导出相应的鲁棒分类器及其实现的错误。对于高斯混合的协方差矩阵是对角的情况下,我们表明,随着输入的维数变大,上界和下界收敛,即我们表征的渐近最优的鲁棒分类。在整个过程中,我们讨论了几个例子,说明有趣的行为,如存在一个相变对手的预算确定是否可以完全抵消对抗扰动的影响。

英文摘要:

It is well-known that machine learning models are vulnerable to small but cleverly-designed adversarial perturbations that can cause misclassification. While there has been major progress in designing attacks and defenses for various adversarial settings, many fundamental and theoretical problems are yet to be resolved. In this paper, we consider classification in the presence of $\ell_0$-bounded adversarial perturbations, a.k.a. sparse attacks. This setting is significantly different from other $\ell_p$-adversarial settings, with $p\geq 1$, as the $\ell_0$-ball is non-convex and highly non-smooth. Under the assumption that data is distributed according to the Gaussian mixture model, our goal is to characterize the optimal robust classifier and the corresponding robust classification error as well as a variety of trade-offs between robustness, accuracy, and the adversary's budget. To this end, we develop a novel classification algorithm called FilTrun that has two main modules: Filtration and Truncation. The key idea of our method is to first filter out the non-robust coordinates of the input and then apply a carefully-designed truncated inner product for classification. By analyzing the performance of FilTrun, we derive an upper bound on the optimal robust classification error. We also find a lower bound by designing a specific adversarial strategy that enables us to derive the corresponding robust classifier and its achieved error. For the case that the covariance matrix of the Gaussian mixtures is diagonal, we show that as the input's dimension gets large, the upper and lower bounds converge; i.e. we characterize the asymptotically-optimal robust classifier. Throughout, we discuss several examples that illustrate interesting behaviors such as the existence of a phase transition for adversary's budget determining whether the effect of adversarial perturbation can be fully neutralized.

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。

↑