Papers with explicit safety mechanisms
MSIA: Adaptive Medical Multimodal Multi-turn Semantic Jailbreak (2026.findings-acl)
Copied to clipboard
| Challenge: | Medical large language models exhibit high domain specificity and condensed semantics, making them vulnerable to diagnostic errors in real-world clinical settings. |
| Approach: | They propose a framework for modeling and inducing multi-turn medical semantic jailbreaks in clinical dialogues. |
| Outcome: | Experiments on chest X-ray-based multimodal medical dialogues show that MSIA outperforms existing jailbreak methods with an average success rate of 76.67%. |