@inproceedings{468cd5d562204687900fe8148f45dbd3,
title = "No offence, Bert - I insult only humans! Multiple addressees sentence-level attack on toxicity detection neural networks",
abstract = "We introduce a simple yet efficient sentence-level attack on black-box toxicity detector models. By adding several positive words or sentences to the end of a hateful message, we are able to change the prediction of a neural network and pass the toxicity detection system check. This approach is shown to be working on seven languages from three different language families. We also describe the defence mechanism against the aforementioned attack and discuss its limitations.",
author = "Sergey Berezin and Reza Farahbakhsh and Noel Crespi",
note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 2023 Findings of the Association for Computational Linguistics: EMNLP 2023 ; Conference date: 06-12-2023 Through 10-12-2023",
year = "2023",
month = jan,
day = "1",
doi = "10.18653/v1/2023.findings-emnlp.155",
language = "English",
series = "Findings of the Association for Computational Linguistics: EMNLP 2023",
publisher = "Association for Computational Linguistics (ACL)",
pages = "2362--2369",
booktitle = "Findings of the Association for Computational Linguistics",
}