Light

Dark

MLingualFC: valuating Jailbreak Vulnerabilities in Multilingual Vision-Language Models

May 28, 2026 약 1분 분량

Jailbreak Jailbreak Attack VLM AI Safety Paper review Safety training Multi-turn attack Black box attack Safety alignment

0. Summary

MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models (Fri, 5 Jun 2026) · #태그
- 요약: 기존 ___에 ___를 더함.
- 의문 / 메모: