Skip to main navigation Skip to search Skip to main content

Attack on Unfair ToS Clause Detection: A Case Study using Universal Adversarial Triggers

  • Technical University of Munich

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

Abstract

Recent work has demonstrated that natural language processing techniques can support consumer protection by automatically detecting unfair clauses in the Terms of Service (ToS) Agreement. This work demonstrates that transformer-based ToS analysis systems are vulnerable to adversarial attacks. We conduct experiments attacking an unfair-clause detector with universal adversarial triggers. Experiments show that a minor perturbation of the text can considerably reduce the detection performance. Moreover, to measure the detectability of the triggers, we conduct a detailed human evaluation study by collecting both answer accuracy and response time from the participants. The results show that the naturalness of the triggers remains key to tricking readers.

Original languageEnglish
Title of host publicationNLLP 2022 - Natural Legal Language Processing Workshop 2022, Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages238-245
Number of pages8
ISBN (Electronic)9781959429180
StatePublished - 2022
Event4th Natural Legal Language Processing Workshop, NLLP 2022, co-located with the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 - Abu Dhabi, United Arab Emirates
Duration: 8 Dec 2022 → …

Publication series

NameNLLP 2022 - Natural Legal Language Processing Workshop 2022, Proceedings of the Workshop

Conference

Conference4th Natural Legal Language Processing Workshop, NLLP 2022, co-located with the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period8/12/22 → …

Fingerprint

Dive into the research topics of 'Attack on Unfair ToS Clause Detection: A Case Study using Universal Adversarial Triggers'. Together they form a unique fingerprint.

Cite this