Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content

Adversarial perturbations can reduce state-of-the-art toxicity classifiers to near-zero accuracy, yet existing defences treat models as black boxes. We apply mechanistic interpretability to toxicity classification for the first time, identifying the internal attention-head circuits responsible for b