Unit 42 researchers developed AdvJudge-Zero, an automated fuzzer that identifies stealthy prompt injection sequences to bypass AI judges. By using low-perplexity formatting tokens, attackers can manipulate LLM-based security gatekeepers into approving harmful content or corrupting training data without triggering traditional detection mechanisms.
AdvJudge-Zero
1 post
Auditing the Gatekeepers: Fuzzing "AI Judges" to Bypass Security Controls