> Auditing the Gatekeepers: Fuzzing "AI Judges" to Bypass Security Controls
[AUTHOR: Tony Li, Hongliang Liu and Yuhao Wu]
[DATE: 10/03/2026 10:00]
[LANGUAGE: EN]
Unit 42 research reveals AI judges are vulnerable to stealthy prompt injection. Benign formatting symbols can bypass security controls.
The post Auditing the Gatekeepers: Fuzzing "AI Judges" to Bypass Security Controls appeared first on Unit 42.