Data Party THU

Aug 11, 2025 · Artificial Intelligence

Can Hidden Signals Reveal Multimodal Model Jailbreaks? Introducing HiddenDetect

This article presents HiddenDetect, a training‑free method that leverages refusal‑semantic vectors and layer‑wise activation analysis to detect jailbreak attempts in multimodal large language models, revealing distinct safety signals across text and image modalities and demonstrating strong performance on several LVLM benchmarks.