Pith. sign in

REVIEW 1 cited by

TextGuard: Provable Defense against Backdoor Attacks on Text Classification

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 2311.11225 v2 pith:TZ3YJOKQ submitted 2023-11-19 cs.LG cs.CR

classification cs.LGcs.CR
keywords attacksbackdoortextguardclassificationdefensedefensesempiricalprovable
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Backdoor attacks have become a major security threat for deploying machine learning models in security-critical applications. Existing research endeavors have proposed many defenses against backdoor attacks. Despite demonstrating certain empirical defense efficacy, none of these techniques could provide a formal and provable security guarantee against arbitrary attacks. As a result, they can be easily broken by strong adaptive attacks, as shown in our evaluation. In this work, we propose TextGuard, the first provable defense against backdoor attacks on text classification. In particular, TextGuard first divides the (backdoored) training data into sub-training sets, achieved by splitting each training sentence into sub-sentences. This partitioning ensures that a majority of the sub-training sets do not contain the backdoor trigger. Subsequently, a base classifier is trained from each sub-training set, and their ensemble provides the final prediction. We theoretically prove that when the length of the backdoor trigger falls within a certain threshold, TextGuard guarantees that its prediction will remain unaffected by the presence of the triggers in training and testing inputs. In our evaluation, we demonstrate the effectiveness of TextGuard on three benchmark text classification tasks, surpassing the certification accuracy of existing certified defenses against backdoor attacks. Furthermore, we propose additional strategies to enhance the empirical performance of TextGuard. Comparisons with state-of-the-art empirical defenses validate the superiority of TextGuard in countering multiple backdoor attacks. Our code and data are available at https://github.com/AI-secure/TextGuard.

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. Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks

    cs.LG 2025-02 reject novelty 5.0 of 10

    FRS targets backdoor triggers with MCTS-guided randomization and parameter smoothing, claiming a larger certified robustness radius that its own theory does not actually prove.

Pith tools