Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks

Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks

1 February 2024

Bryan A. Plummer

Papers citing "Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks"

9 / 9 papers shown

Title
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models J. Liu Hangyu Guo Ranjie Duan Xingyuan Bu Yancheng He ... Yingshui Tan Yanan Wu Jihao Gu Y. Li J. Zhu MLLM 103 0 0 25 Apr 2025
SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models Justus Westerhoff Erblina Purellku Jakob Hackstein Jonas Loos Leo Pinetzki Lorenz Hufe AAML 28 0 0 07 Apr 2025
Web Artifact Attacks Disrupt Vision Language Models Maan Qraitem Piotr Teterwak Kate Saenko Bryan A. Plummer AAML 73 0 0 17 Mar 2025
New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook Meng Yang Tianqing Zhu Chi Liu Wanlei Zhou Shui Yu Philip S. Yu AAML ELM PILM 56 1 0 12 Nov 2024
A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends Daizong Liu Mingyu Yang Xiaoye Qu Pan Zhou Yu Cheng Wei Hu ELM AAML 30 25 0 10 Jul 2024
Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt Zonghao Ying Aishan Liu Tianyuan Zhang Zhengmin Yu Siyuan Liang Xianglong Liu Dacheng Tao AAML 33 26 0 06 Jun 2024
Typography Leads Semantic Diversifying: Amplifying Adversarial Transferability across Multimodal Large Language Models Hao-Ran Cheng Erjia Xiao Jiahang Cao Le Yang Kaidi Xu Jindong Gu Renjing Xu AAML 55 7 0 30 May 2024
Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography N. Chung Sensen Gao Tuan-Anh Vu Jie M. Zhang Aishan Liu Yun Lin Jin Song Dong Qi Guo AAML 35 9 0 23 May 2024
Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security Yihe Fan Yuxin Cao Ziyu Zhao Ziyao Liu Shaofeng Li 27 12 0 08 Apr 2024