A Closer Look at the Adversarial Robustness of Information Bottleneck Models

Alexander A. Alemi; David Stutz; Iryna Korshunova; Olivia Wiles; Sven Gowal

A Closer Look at the Adversarial Robustness of Information Bottleneck Models

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 2107.05712 v1 pith:6PIRSART submitted 2021-07-12 cs.LG

Iryna Korshunova , David Stutz , Alexander A. Alemi , Olivia Wiles , Sven Gowal This is my paper

classification cs.LG

keywords informationadversarialmodelsrobustnessbottleneckbottleneckspreviousalone

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

abstract

We study the adversarial robustness of information bottleneck models for classification. Previous works showed that the robustness of models trained with information bottlenecks can improve upon adversarial training. Our evaluation under a diverse range of white-box $l_{\infty}$ attacks suggests that information bottlenecks alone are not a strong defense strategy, and that previous results were likely influenced by gradient obfuscation.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

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

When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers
cs.LG 2026-05 unverdicted novelty 7.0 of 10

Concept-level adversarial attacks exploit CBM interpretability on the CUB dataset, but SPECTRA raises required perturbation norm from 0.46 to over 4200 while keeping accuracy loss under 2.2%.

Pith tools