Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based Moderation
A rejudge protocol is introduced that extends direct contradiction with decision-boundary perturbations and adversarial rationales to address the susceptibility of initially correct model judgments to annotator-style rebuttals and whether attack effectiveness differs across manipulation directions.
Junyu Lu, Kaiyuan Liu, Kai-Chun Wang et al.
· 0 citations