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 2102.11069cs.LGcs.AIstat.ML
收藏

对抗鲁棒性的PAC-Bayes分析

A PAC-Bayes Analysis of Adversarial Robustness

Univ Lyon, UJM-Saint-Etienne, CNRS, Institut d Optique Graduate School, Laboratoire Hubert Curien UMR 5516(里昂大学,圣埃蒂安让·莫内大学,法国国家科学研究中心,光学研究生院,于贝尔·居里安实验室 UMR 5516);Airbus Opération S.A.S(空中客车运营公司);University of Toulouse, Institut de Recherche en Informatique de Toulouse(图卢兹大学,图卢兹信息研究所)

Paul Viallard, Guillaume Vidot, Amaury Habrard, Emilie Morvant

摘要:

我们提出了对抗鲁棒性的第一个通用PAC-贝叶斯泛化边界,该边界估计在测试时,模型对输入中不可感知的扰动具有多大的不变性。我们利用PAC-Bayesian框架来约束大多数投票(在整个假设类中)的扰动的平均风险,而不是在所有可能的扰动中得出假设风险的最坏情况分析。我们理论上建立的分析具有提供对任何类型的攻击有效的一般界限(i)的优点(即,对抗攻击),(ii)由于PAC-贝叶斯框架而紧密,(iii)可以在学习阶段直接最小化,以在测试时获得对不同攻击的鲁棒模型。

英文摘要:

We propose the first general PAC-Bayesian generalization bounds for adversarial robustness, that estimate, at test time, how much a model will be invariant to imperceptible perturbations in the input. Instead of deriving a worst-case analysis of the risk of a hypothesis over all the possible perturbations, we leverage the PAC-Bayesian framework to bound the averaged risk on the perturbations for majority votes (over the whole class of hypotheses). Our theoretically founded analysis has the advantage to provide general bounds (i) that are valid for any kind of attacks (i.e., the adversarial attacks), (ii) that are tight thanks to the PAC-Bayesian framework, (iii) that can be directly minimized during the learning phase to obtain a robust model on different attacks at test time.

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。

↑