No offence, Bert - I insult only humans! Multilingual sentence-level attack on toxicity detection networks
Sergey Berezin, Reza Farahbakhsh, Noël Crespi · 2023
We introduce a simple yet efficient sentencelevel 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.