作者位次 #3/4ACL 2026Poster· Natural Language Processing
GAMBIT : A Gamified Jailbreak Framework for Multimodal Large Language Models
Xiangdong Hu · Yangyang Jiang · Qin Hu · Xiaojun Jia
摘要
Multimodal Large Language Models (MLLMs) have become widely deployed, yet their safety alignment remains fragile under adversarial inputs. Previous work has shown that increasing inference steps can disrupt safety mechanisms and lead MLLMs to generate attacker-desired harmful content. However, mo...