VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration

26 May 2025

Papers citing "VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration"

3 / 3 papers shown

Title
Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Jiahui Geng Thy Thy Tran Preslav Nakov Iryna Gurevych MLLM AAML 34 0 0 31 May 2025
Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update Qing Li Jiahui Geng Zongxiong Chen Kun Song Lei Ma Fakhri Karray KELM LLMSV 73 6 0 24 Jan 2025
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 231 160 0 09 Nov 2023