v1v2 (latest)

JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models

26 May 2025

Papers citing "JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models"

3 / 3 papers shown

Title
Qwen2.5-VL Technical Report S. Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge ... Zesen Cheng Hang Zhang Zhibo Yang Haiyang Xu Junyang Lin VLM 435 699 0 20 Feb 2025
Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models Yifan Li Hangyu Guo Kun Zhou Wayne Xin Zhao Ji-Rong Wen 130 56 0 14 Mar 2024
FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts Yichen Gong Delong Ran Jinyuan Liu Conglei Wang Tianshuo Cong Anyu Wang Sisi Duan Xiaoyun Wang MLLM 235 160 0 09 Nov 2023