Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink

28 January 2025

Papers citing "Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink"

50 / 72 papers shown

Title
Grounded Chain-of-Thought for Multimodal Large Language Models Qiong Wu Xiangcong Yang Yiyi Zhou Chenxin Fang Baiyang Song Xiaoshuai Sun Rongrong Ji LRM 151 2 0 17 Mar 2025
GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis Bo Liu K. Zou Liming Zhan Zexin Lu Xiaoyu Dong Yidi Chen Chengqiang Xie Jiannong Cao Xiao-Ming Wu Huazhu Fu 174 2 0 25 Nov 2024
MME-Finance: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning Ziliang Gan Yu Lu D. Zhang Haohan Li Che Liu ... Haipang Wu Chaoyou Fu Z. Xu Rongjunchen Zhang Yong Dai 92 10 0 05 Nov 2024
IPL: Leveraging Multimodal Large Language Models for Intelligent Product Listing Kang Chen Qingheng Zhang Chengbao Lian Yixin Ji Xuwei Liu Shuguang Han Guoqiang Wu Fei Huang Jufeng Chen 61 2 0 22 Oct 2024
Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate Zheng Lin Zhenxing Niu Zhibin Wang Yinghui Xu 60 6 0 30 Jul 2024
MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity Yangzhou Liu Yue Cao Zhangwei Gao Weiyun Wang Zhe Chen ... Lewei Lu Xizhou Zhu Tong Lu Yu Qiao Jifeng Dai VLM MLLM 92 26 0 22 Jul 2024
Multi-Object Hallucination in Vision-Language Models Xuweiyi Chen Ziqiao Ma Xuejun Zhang Sihan Xu Shengyi Qian Jianing Yang David Fouhey Joyce Chai 66 20 0 08 Jul 2024
Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration Zhongzhi Yu Zheng Wang Yonggan Fu Huihong Shi Khalid Shaikh Yingyan Celine Lin 97 25 0 22 Jun 2024
Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization Seungwoo Son Wonpyo Park Woohyun Han Kyuyeun Kim Jaeho Lee MQ 59 13 0 17 Jun 2024
Yo'LLaVA: Your Personalized Language and Vision Assistant Thao Nguyen Haotian Liu Yuheng Li Mu Cai Utkarsh Ojha Yong Jae Lee VLM MLLM 88 22 0 13 Jun 2024
Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks Zonghao Ying Aishan Liu Xianglong Liu Dacheng Tao 92 22 0 10 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 110 10 0 30 May 2024
Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character Siyuan Ma Weidi Luo Yu Wang Xiaogeng Liu 120 27 0 25 May 2024
An Empirical Study and Analysis of Text-to-Image Generation Using Large Language Model-Powered Textual Representation Zhiyu Tan Mengping Yang Luozheng Qin Hao Yang Ye Qian Qiang-feng Zhou Cheng Zhang Hao Li 96 6 0 21 May 2024
Adversarial Robustness for Visual Grounding of Multimodal Large Language Models Kuofeng Gao Yang Bai Jiawang Bai Yong Yang Shu-Tao Xia AAML 79 19 0 16 May 2024
Hallucination of Multimodal Large Language Models: A Survey Zechen Bai Pichao Wang Tianjun Xiao Tong He Zongbo Han Zheng Zhang Mike Zheng Shou VLM LRM 175 181 0 29 Apr 2024
Harnessing GPT-4V(ision) for Insurance: A Preliminary Exploration Chenwei Lin Hanjia Lyu Jiebo Luo Xian Xu LM&MA MLLM 29 2 0 15 Apr 2024
AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting Yu Wang Xiaogeng Liu Yu-Feng Li Muhao Chen Chaowei Xiao AAML 79 57 0 14 Mar 2024
Jailbreaking Attack against Multimodal Large Language Model Zhenxing Niu Haoxuan Ji Xinbo Gao Gang Hua Rong Jin 72 70 0 04 Feb 2024
Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images Kuofeng Gao Yang Bai Jindong Gu Shu-Tao Xia Philip Torr Zhifeng Li Wei Liu VLM 71 43 0 20 Jan 2024
Gemini Pro Defeated by GPT-4V: Evidence from Education Gyeong-Geon Lee Ehsan Latif Lehong Shi Xiaoming Zhai 68 24 0 27 Dec 2023
ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation Xiaoqi Li Mingxu Zhang Yiran Geng Haoran Geng Yuxing Long Yan Shen Renrui Zhang Jiaming Liu Hao Dong LM&Ro LRM 96 94 0 24 Dec 2023
Hallucination Augmented Contrastive Learning for Multimodal Large Language Model Chaoya Jiang Haiyang Xu Mengfan Dong Jiaxing Chen Wei Ye Mingshi Yan Qinghao Ye Ji Zhang Fei Huang Shikun Zhang VLM 41 57 0 12 Dec 2023
On the Robustness of Large Multimodal Models Against Image Adversarial Attacks Xuanimng Cui Alejandro Aparcedo Young Kyun Jang Ser-Nam Lim AAML VLM 48 43 0 06 Dec 2023
RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback M. Steyvers Yuan Yao Haoye Zhang Taiwen He Yifeng Han ... Xinyue Hu Zhiyuan Liu Hai-Tao Zheng Maosong Sun Tat-Seng Chua MLLM VLM 179 214 0 01 Dec 2023
OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation Qidong Huang Xiao-wen Dong Pan Zhang Bin Wang Conghui He Jiaqi Wang Dahua Lin Weiming Zhang Neng H. Yu MLLM 120 197 0 29 Nov 2023
Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding Sicong Leng Hang Zhang Guanzheng Chen Xin Li Shijian Lu Chunyan Miao Li Bing VLM MLLM 141 229 0 28 Nov 2023
Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization Zhiyuan Zhao Bin Wang Linke Ouyang Xiao-wen Dong Jiaqi Wang Conghui He MLLM VLM 103 131 0 28 Nov 2023
HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data Qifan Yu Juncheng Li Longhui Wei Liang Pang Wentao Ye Bosheng Qin Siliang Tang Qi Tian Yueting Zhuang MLLM VLM 93 76 0 22 Nov 2023
ShareGPT4V: Improving Large Multi-Modal Models with Better Captions Lin Chen Jinsong Li Xiao-wen Dong Pan Zhang Conghui He Jiaqi Wang Feng Zhao Dahua Lin MLLM VLM 188 660 0 21 Nov 2023
LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge Gongwei Chen Leyang Shen Rui Shao Xiang Deng Liqiang Nie VLM MLLM 86 48 0 20 Nov 2023
AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation Junyang Wang Yuhang Wang Guohai Xu Jing Zhang Yukai Gu ... Jiaqi Wang Haiyang Xu Ming Yan Ji Zhang Jitao Sang MLLM VLM 64 117 0 13 Nov 2023
Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision Seongyun Lee Sue Hyun Park Yongrae Jo Minjoon Seo 50 61 0 13 Nov 2023
Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models Zhang Li Biao Yang Qiang Liu Zhiyin Ma Shuo Zhang Jingxu Yang Yabo Sun Yuliang Liu Xiang Bai MLLM 91 270 0 11 Nov 2023
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 211 150 0 09 Nov 2023
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification Mintong Kang Basel Alomair Yue Liu 71 32 0 27 Oct 2023
HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models Tianrui Guan Fuxiao Liu Xiyang Wu Ruiqi Xian Zongxia Li ... Lichang Chen Furong Huang Yaser Yacoob Dinesh Manocha Dinesh Manocha VLM MLLM 94 182 0 23 Oct 2023
Can GPT-4V(ision) Serve Medical Applications? Case Studies on GPT-4V for Multimodal Medical Diagnosis Chaoyi Wu Jiayu Lei Qiaoyu Zheng Weike Zhao Weixiong Lin ... Xiao Zhou Ziheng Zhao Ya Zhang Yanfeng Wang Weidi Xie LM&MA 138 78 0 15 Oct 2023
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning Jun Chen Deyao Zhu Xiaoqian Shen Xiang Li Zechun Liu Pengchuan Zhang Raghuraman Krishnamoorthi Vikas Chandra Yunyang Xiong Mohamed Elhoseiny MLLM 236 465 0 14 Oct 2023
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model Jiabo Ye Anwen Hu Haiyang Xu Qinghao Ye Mingshi Yan ... Ji Zhang Qin Jin Liang He Xin Lin Feiyan Huang VLM MLLM 178 91 0 08 Oct 2023
Improved Baselines with Visual Instruction Tuning Haotian Liu Chunyuan Li Yuheng Li Yong Jae Lee VLM MLLM 118 2,725 0 05 Oct 2023
DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model Zhenhua Xu Yujia Zhang Enze Xie Zhen Zhao Yong Guo Kwan-Yee. K. Wong Zhenguo Li Hengshuang Zhao MLLM 71 292 0 02 Oct 2023
Analyzing and Mitigating Object Hallucination in Large Vision-Language Models Yiyang Zhou Chenhang Cui Jaehong Yoon Linjun Zhang Zhun Deng Chelsea Finn Mohit Bansal Huaxiu Yao MLLM 109 181 0 01 Oct 2023
Efficient Streaming Language Models with Attention Sinks Michel Lang Yuandong Tian Beidi Chen Song Han Mike Lewis AI4TS RALM 125 758 0 29 Sep 2023
Vision Transformers Need Registers Zilong Chen Maxime Oquab Julien Mairal Huaping Liu ViT 164 343 0 28 Sep 2023
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models Erfan Shayegani Yue Dong Nael B. Abu-Ghazaleh 94 147 0 26 Jul 2023
Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic Ke Chen Zhao Zhang Weili Zeng Richong Zhang Feng Zhu Rui Zhao ObjD 85 638 0 27 Jun 2023
Kosmos-2: Grounding Multimodal Large Language Models to the World Zhiliang Peng Wenhui Wang Li Dong Y. Hao Shaohan Huang Shuming Ma Furu Wei MLLM ObjD VLM 104 755 0 26 Jun 2023
Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning Fuxiao Liu Kevin Qinghong Lin Linjie Li Jianfeng Wang Yaser Yacoob Lijuan Wang VLM MLLM 105 279 0 26 Jun 2023
Visual Adversarial Examples Jailbreak Aligned Large Language Models Xiangyu Qi Kaixuan Huang Ashwinee Panda Peter Henderson Mengdi Wang Prateek Mittal AAML 81 158 0 22 Jun 2023