All You Need is "Leet": Evading Hate-speech Detection AI
Not on the map. Why?
Abstract (arXiv)
Social media and online forums are increasingly becoming popular. Unfortunately, these platforms are being used for spreading hate speech. In this paper, we design black-box techniques to protect users from hate-speech on online platforms by generating perturbations that can fool state of the art deep learning based hate speech detection models thereby decreasing their efficiency. We also ensure a minimal change in the original meaning of hate-speech. Our best perturbation attack is successfully able to evade hate-speech detection for 86.8 % of hateful text.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 6 of its 20 references that are in the map. First posted on arXiv 22 May 2025.
Builds on
6 of 20 references.
References · 6
- 2017Automated Hate Speech Detection and the Problem of Offensive Languagecited by 736
- 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 381
- 2017Deceiving Google's Perspective API Built for Detecting Toxic Commentscited by 102
- 2018Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examplescited by 94
- 2017Robust Physical-World Attacks on Deep Learning Modelscited by 72
- 2018All You Need is "Love": Evading Hate-speech Detectioncited by 56
Built on by
Citing papers per year: 2026: 1.
1 paper.