Image-to-Text Logic Jailbreak: Your Imagination can Help You Do Anything

v1v2 (latest)

Image-to-Text Logic Jailbreak: Your Imagination can Help You Do Anything

1 July 2024

ArXiv (abs)PDF HTML

Papers citing "Image-to-Text Logic Jailbreak: Your Imagination can Help You Do Anything"

7 / 7 papers shown

Title
How Far Are We from Intelligent Visual Deductive Reasoning? Yizhe Zhang Richard He Bai Ruixiang Zhang Jiatao Gu Shuangfei Zhai J. Susskind Navdeep Jaitly ReLM LRM 77 17 0 07 Mar 2024
GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts Jiahao Yu Xingwei Lin Zheng Yu Xinyu Xing SILM 185 342 0 19 Sep 2023
Universal and Transferable Adversarial Attacks on Aligned Language Models Andy Zou Zifan Wang Nicholas Carlini Milad Nasr J. Zico Kolter Matt Fredrikson 291 1,498 0 27 Jul 2023
On Evaluating Adversarial Robustness of Large Vision-Language Models Yunqing Zhao Tianyu Pang Chao Du Xiao Yang Chongxuan Li Ngai-Man Cheung Min Lin VLM AAML MLLM 115 175 0 26 May 2023
Model Extraction and Adversarial Transferability, Your BERT is Vulnerable! Xuanli He Lingjuan Lyu Xingliang Yuan Lichao Sun MIACV SILM 79 96 0 18 Mar 2021
A Survey On Universal Adversarial Attack Chaoning Zhang Philipp Benz Chenguo Lin Adil Karjauv Jing Wu In So Kweon AAML 60 93 0 02 Mar 2021
Explaining and Harnessing Adversarial Examples Ian Goodfellow Jonathon Shlens Christian Szegedy AAML GAN 280 19,107 0 20 Dec 2014