arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.04065stat.MLcs.LG
收藏

对抗鲁棒性的广义无免费午餐定理

Generalized No Free Lunch Theorem for Adversarial Robustness

Criteo(Criteo公司)

Elvis Dohmatob

摘要:

这份手稿提出了一些新的不可能的结果对抗的鲁棒性在机器学习,一个非常重要的,但很大程度上是开放的问题。我们证明了,如果以类标号为条件,数据分布满足$W_2$ Talagrand运输成本不等式(例如,如果条件分布的密度是对数凹的,则满足这个条件;是具有正Ricci曲率的紧致黎曼流形上的一致测度,一旦扰动稍微大于问题中的自然噪声水平,则任何分类器都可能以高概率被反向欺骗。我们把这个结果称为强“没有免费午餐”定理,作为最近的一些结果(Tsipras et al. 2018,Fawzi et al. 2018,etc.)。可以立即恢复为非常特殊的情况。我们的理论界模拟和真实数据(MNIST)证明。最后,我们对未来可能的研究方向进行了一些推测。

英文摘要:

This manuscript presents some new impossibility results on adversarial robustness in machine learning, a very important yet largely open problem. We show that if conditioned on a class label the data distribution satisfies the $W_2$ Talagrand transportation-cost inequality (for example, this condition is satisfied if the conditional distribution has density which is log-concave; is the uniform measure on a compact Riemannian manifold with positive Ricci curvature, any classifier can be adversarially fooled with high probability once the perturbations are slightly greater than the natural noise level in the problem. We call this result The Strong "No Free Lunch" Theorem as some recent results (Tsipras et al. 2018, Fawzi et al. 2018, etc.) on the subject can be immediately recovered as very particular cases. Our theoretical bounds are demonstrated on both simulated and real data (MNIST). We conclude the manuscript with some speculation on possible future research directions.

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。

↑