arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.10022cs.LG
收藏

对抗分类的一致性

Towards Consistency in Adversarial Classification

Meta AI Research(Meta人工智能研究院);Université Paris-Dauphine(巴黎多芬大学);Ecole Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院)

Laurent Meunier, Raphaël Ettedgui, Rafael Pinot, Yann Chevaleyre, Jamal Atif

摘要:

在本文中,我们研究了在对抗性例子的背景下的一致性问题。具体来说,我们解决了以下问题:代理损失仍然可以被用作代理最小化的$0/1$损失的对手,在测试时改变输入的存在?与标准分类任务不同,这个问题不能简化为逐点最小化问题,并且校准不需要足以确保一致性。在本文中,我们揭示了一些特定于对抗问题的病态行为,并表明在这种情况下,没有凸代理损失是一致的或校准的。因此,有必要设计另一类代理函数来解决对抗性一致性问题。作为设计这样一个类的第一步,我们确定了在对抗和标准设置中校准代理损失的充分和必要条件。最后,我们给出了一些方向,以建立一类损失,可以在对抗框架中保持一致。

英文摘要:

In this paper, we study the problem of consistency in the context of adversarial examples. Specifically, we tackle the following question: can surrogate losses still be used as a proxy for minimizing the $0/1$ loss in the presence of an adversary that alters the inputs at test-time? Different from the standard classification task, this question cannot be reduced to a point-wise minimization problem, and calibration needs not to be sufficient to ensure consistency. In this paper, we expose some pathological behaviors specific to the adversarial problem, and show that no convex surrogate loss can be consistent or calibrated in this context. It is therefore necessary to design another class of surrogate functions that can be used to solve the adversarial consistency issue. As a first step towards designing such a class, we identify sufficient and necessary conditions for a surrogate loss to be calibrated in both the adversarial and standard settings. Finally, we give some directions for building a class of losses that could be consistent in the adversarial framework.

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。

↑