Pith. sign in

REVIEW 2 cited by

Not yet reviewed by Pith; the record is open.

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 1804.03286 v1 pith:ZRXUTLB5 submitted 2018-04-10 cs.CV cs.CRcs.LGstat.ML

On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses

classification cs.CV cs.CRcs.LGstat.ML
keywords adversarialcvprdefenseswhite-boxaccuracyappearedapplyingdefended
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Neural networks are known to be vulnerable to adversarial examples. In this note, we evaluate the two white-box defenses that appeared at CVPR 2018 and find they are ineffective: when applying existing techniques, we can reduce the accuracy of the defended models to 0%.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

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

  1. Stateful Detection of Black-Box Adversarial Attacks

    cs.CR 2019-07 unverdicted novelty 7.0

    The paper argues for stateful defenses over stateless ones to detect adversarial example generation via query history and introduces query blinding as a counter-attack.

  2. Connecting Lyapunov Control Theory to Adversarial Attacks

    cs.CR 2019-07 unverdicted novelty 5.0

    Connects Lyapunov control theory to a provable defense against weaker adversarial attacks on neural networks.