From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking

From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking

21 June 2024

Siyuan Wang

Papers citing "From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking"

6 / 6 papers shown

Title
JailBreakV-28K: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks Weidi Luo Siyuan Ma Xiaogeng Liu Xiaoyu Guo Chaowei Xiao AAML 58 17 0 03 Apr 2024
Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue Zhenhong Zhou Jiuyang Xiang Haopeng Chen Quan Liu Zherui Li Sen Su 29 6 0 27 Feb 2024
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding Zhangchen Xu Fengqing Jiang Luyao Niu Jinyuan Jia Bill Yuchen Lin Radha Poovendran AAML 129 82 0 14 Feb 2024
Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast Xiangming Gu Xiaosen Zheng Tianyu Pang Chao Du Qian Liu Ye Wang Jing Jiang Min-Bin Lin LLMAG LM&Ro 35 47 0 13 Feb 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 127 116 0 09 Nov 2023
GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts Jiahao Yu Xingwei Lin Zheng Yu Xinyu Xing SILM 110 292 0 19 Sep 2023