Probabilistic Margins for Instance Reweighting in Adversarial Training

Qizhou WANG, Feng Liu, Bo HAN*, Tongliang Liu, Chen Gong, Gang Niu, Mingyuan Zhou, Masashi Sugiyama

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

Abstract

Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights. However, existing methods measuring the closeness are not very reliable: they are discrete and can take only a few values, and they are path-dependent, i.e., they may change given the same start and end points with different attack paths. In this paper, we propose three types of probabilistic margin (PM), which are continuous and path-independent, for measuring the aforementioned closeness and reweighting adversarial data. Specifically, a PM is defined as the difference between two estimated class-posterior probabilities, e.g., such the probability of the true label minus the probability of the most confusing label given some natural data. Though different PMs capture different geometric properties, all three PMs share a negative correlation with the vulnerability of data: data with larger/smaller PMs are safer/riskier and should have smaller/larger weights. Experiments demonstrate that PMs are reliable measurements and PM-based reweighting methods outperform state-of-the-art methods.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 34 (NeurIPS 2021)
EditorsM. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, J. Wortman Vaughan
PublisherNeural Information Processing Systems Foundation
Number of pages12
Publication statusPublished - 6 Dec 2021
Event35th Conference on Neural Information Processing Systems - Virtual
Duration: 6 Dec 202114 Dec 2021

Publication series

NameNeurIPS Proceedings

Conference

Conference35th Conference on Neural Information Processing Systems
Abbreviated titleNeurIPS 2021
Period6/12/2114/12/21

Fingerprint

Dive into the research topics of 'Probabilistic Margins for Instance Reweighting in Adversarial Training'. Together they form a unique fingerprint.

Cite this