"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks

Edoardo Mosca, Javier Rando-Ramirez, Shreyash Agarwal, Georg Groh

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Scopus citations

Abstract

Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extensive research in computer vision has been carried to develop reliable defense strategies. However, the same issue remains less explored in natural language processing. Our work presents a model-agnostic detector of adversarial text examples. The approach identifies patterns in the logits of the target classifier when perturbing the input text. The proposed detector improves the current state-of-the-art performance in recognizing adversarial inputs and exhibits strong generalization capabilities across different NLP models, datasets, and word-level attacks.

Original languageEnglish
Title of host publicationACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
EditorsSmaranda Muresan, Preslav Nakov, Aline Villavicencio
PublisherAssociation for Computational Linguistics (ACL)
Pages7806-7816
Number of pages11
ISBN (Electronic)9781955917216
StatePublished - 2022
Event60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 - Dublin, Ireland
Duration: 22 May 202227 May 2022

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume1
ISSN (Print)0736-587X

Conference

Conference60th Annual Meeting of the Association for Computational Linguistics, ACL 2022
Country/TerritoryIreland
CityDublin
Period22/05/2227/05/22

Fingerprint

Dive into the research topics of '"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks'. Together they form a unique fingerprint.

Cite this