@inproceedings{1f5f104394a24ac88aa633e96325c940,
title = "Attack on Unfair ToS Clause Detection: A Case Study using Universal Adversarial Triggers",
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.",
author = "Shanshan Xu and Irina Broda and Rashid Haddad and Marco Negrini and Matthias Grabmair",
note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 4th Natural Legal Language Processing Workshop, NLLP 2022, co-located with the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 ; Conference date: 08-12-2022",
year = "2022",
language = "English",
series = "NLLP 2022 - Natural Legal Language Processing Workshop 2022, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "238--245",
booktitle = "NLLP 2022 - Natural Legal Language Processing Workshop 2022, Proceedings of the Workshop",
}