On Norm-Agnostic Robustness of Adversarial Training

Bai Li; Changyou Chen; Lawrence Carin; Wenlin Wang

On Norm-Agnostic Robustness of Adversarial Training

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1905.06455 v1 pith:62RN5DWW submitted 2019-05-15 cs.LG cs.CRstat.ML

Bai Li , Changyou Chen , Wenlin Wang , Lawrence Carin This is my paper · ORCID

classification cs.LGcs.CRstat.ML

keywords adversarialtrainingexamplesrobustnessattackcarefullydatadefense

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

abstract

Adversarial examples are carefully perturbed in-puts for fooling machine learning models. A well-acknowledged defense method against such examples is adversarial training, where adversarial examples are injected into training data to increase robustness. In this paper, we propose a new attack to unveil an undesired property of the state-of-the-art adversarial training, that is it fails to obtain robustness against perturbations in $\ell_2$ and $\ell_\infty$ norms simultaneously. We discuss a possible solution to this issue and its limitations as well.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition
cs.LG 2025-09 conditional novelty 5.0 of 10

A single prior network distilled from a 50-member self-supervised ensemble matches ensemble accuracy and robustness on HAR benchmarks at single-model inference cost.

Pith tools