Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors

17 May 2024

Papers citing "Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors"

29 / 29 papers shown

Title
Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation Yinuo Liu Zenghui Yuan Guiyao Tie Jiawen Shi Lichao Sun Lichao Sun Neil Zhenqiang Gong 104 2 0 08 Mar 2025
Optimization-based Prompt Injection Attack to LLM-as-a-Judge Jiawen Shi Zenghui Yuan Yinuo Liu Yue Huang Pan Zhou Lichao Sun Neil Zhenqiang Gong AAML 144 57 0 26 Mar 2024
PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses Chong Xiang Tong Wu Sihui Dai Jonathan Petit Suman Jana Prateek Mittal 120 6 0 19 Oct 2023
PaLI-3 Vision Language Models: Smaller, Faster, Stronger Xi Chen Xiao Wang Lucas Beyer Alexander Kolesnikov Jialin Wu ... Keran Rong Tianli Yu Daniel Keysers Xiao-Qi Zhai Radu Soricut MLLM VLM 121 104 0 13 Oct 2023
Jailbreaking Black Box Large Language Models in Twenty Queries Patrick Chao Alexander Robey Yan Sun Hamed Hassani George J. Pappas Eric Wong AAML 142 709 0 12 Oct 2023
Improved Baselines with Visual Instruction Tuning Haotian Liu Chunyuan Li Yuheng Li Yong Jae Lee VLM MLLM 181 2,826 0 05 Oct 2023
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks Alexander Robey Eric Wong Hamed Hassani George J. Pappas AAML 126 257 0 05 Oct 2023
Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection Lukas Strack Futa Waseda H. Nguyen Yinqiang Zheng Isao Echizen AAML 80 2 0 27 Sep 2023
Image Hijacks: Adversarial Images can Control Generative Models at Runtime Luke Bailey Euan Ong Stuart J. Russell Scott Emmons VLM MLLM 89 87 0 01 Sep 2023
DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing Jiawei Zhang Zhongzhu Chen Huan Zhang Chaowei Xiao Yue Liu DiffM 82 26 0 28 Aug 2023
Universal and Transferable Adversarial Attacks on Aligned Language Models Andy Zou Zifan Wang Nicholas Carlini Milad Nasr J. Zico Kolter Matt Fredrikson 295 1,518 0 27 Jul 2023
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models Erfan Shayegani Yue Dong Nael B. Abu-Ghazaleh 109 152 0 26 Jul 2023
Prompt Injection attack against LLM-integrated Applications Yi Liu Gelei Deng Yuekang Li Kailong Wang Zihao Wang ... Tianwei Zhang Yepang Liu Haoyu Wang Yanhong Zheng Yang Liu SILM 116 363 0 08 Jun 2023
Vision-Language Models for Vision Tasks: A Survey Jingyi Zhang Jiaxing Huang Sheng Jin Shijian Lu VLM 158 550 0 03 Apr 2023
Robust Evaluation of Diffusion-Based Adversarial Purification M. Lee Dongwoo Kim 132 63 0 16 Mar 2023
GPT-4 Technical Report OpenAI OpenAI OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad ... Shengjia Zhao Tianhao Zheng Juntang Zhuang William Zhuk Barret Zoph LLMAG MLLM 1.5K 14,761 0 15 Mar 2023
Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection Kai Greshake Sahar Abdelnabi Shailesh Mishra C. Endres Thorsten Holz Mario Fritz SILM 153 498 0 23 Feb 2023
Pretraining Language Models with Human Preferences Tomasz Korbak Kejian Shi Angelica Chen Rasika Bhalerao C. L. Buckley Jason Phang Sam Bowman Ethan Perez ALM SyDa 93 230 0 16 Feb 2023
Aligning Language Models with Preferences through f-divergence Minimization Dongyoung Go Tomasz Korbak Germán Kruszewski Jos Rozen Nahyeon Ryu Marc Dymetman 81 76 0 16 Feb 2023
Better Diffusion Models Further Improve Adversarial Training Zekai Wang Tianyu Pang Chao Du Min Lin Weiwei Liu Shuicheng Yan DiffM 93 227 0 09 Feb 2023
Constitutional AI: Harmlessness from AI Feedback Yuntao Bai Saurav Kadavath Sandipan Kundu Amanda Askell John Kernion ... Dario Amodei Nicholas Joseph Sam McCandlish Tom B. Brown Jared Kaplan SyDa MoMe 214 1,646 0 15 Dec 2022
DensePure: Understanding Diffusion Models towards Adversarial Robustness Chaowei Xiao Zhongzhu Chen Kun Jin Jiong Wang Weili Nie Mingyan D. Liu Anima Anandkumar Yue Liu Basel Alomair DiffM 110 38 0 01 Nov 2022
Training language models to follow instructions with human feedback Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright ... Amanda Askell Peter Welinder Paul Christiano Jan Leike Ryan J. Lowe OSLM ALM 900 13,228 0 04 Mar 2022
PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier Chong Xiang Saeed Mahloujifar Prateek Mittal VLM AAML 87 77 0 20 Aug 2021
Towards Defending against Adversarial Examples via Attack-Invariant Features Dawei Zhou Tongliang Liu Bo Han N. Wang Chunlei Peng Xinbo Gao AAML 77 45 0 09 Jun 2021
Certified Adversarial Robustness via Randomized Smoothing Jeremy M. Cohen Elan Rosenfeld J. Zico Kolter AAML 173 2,052 0 08 Feb 2019
Object Detection with Deep Learning: A Review Zhong-Qiu Zhao Peng Zheng Shou-tao Xu Xindong Wu ObjD 139 4,024 0 15 Jul 2018
Adversarial Patch Tom B. Brown Dandelion Mané Aurko Roy Martín Abadi Justin Gilmer AAML 93 1,097 0 27 Dec 2017
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images Anh Totti Nguyen J. Yosinski Jeff Clune AAML 176 3,275 0 05 Dec 2014