Pith. sign in

REVIEW 1 cited by

BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense

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 2301.06241 v1 pith:B6EGUQ3O submitted 2023-01-16 cs.CR cs.LG

classification cs.CRcs.LG
keywords backdoorattacksattacktriggersforensicsinputsmodelscanners
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep Learning backdoor attacks have a threat model similar to traditional cyber attacks. Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks. In this paper, we propose a novel model backdoor forensics technique. Given a few attack samples such as inputs with backdoor triggers, which may represent different types of backdoors, our technique automatically decomposes them to clean inputs and the corresponding triggers. It then clusters the triggers based on their properties to allow automatic attack categorization and summarization. Backdoor scanners can then be automatically synthesized to find other instances of the same type of backdoor in other models. Our evaluation on 2,532 pre-trained models, 10 popular attacks, and comparison with 9 baselines show that our technique is highly effective. The decomposed clean inputs and triggers closely resemble the ground truth. The synthesized scanners substantially outperform the vanilla versions of existing scanners that can hardly generalize to different kinds of attacks.

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

  1. TracLLM: A Generic Framework for Attributing Long Context LLMs

    cs.CR 2025-06 conditional novelty 6.0 of 10

    TracLLM traces an LLM output back to the specific text passages in a long context that caused it, using hierarchical group scoring with denoising and ensembling.

Pith tools