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

• URL: http://arxiv.org/abs/2501.15269v1
• Date: Sat, 25 Jan 2025 16:36:00 GMT
• Title: Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink
• Authors: Yining Wang, Mi Zhang, Junjie Sun, Chenyue Wang, Min Yang, Hui Xue, Jialing Tao, Ranjie Duan, Jiexi Liu,
• Abstract summary: Multi-modal Large Language Models (MLLMs) are revolutionizing visual-language applications. Yet, these models are often plagued by the hallucination problem, which involves generating inaccurate objects, attributes, and relationships that do not match the visual content. We propose a novel hallucination attack against MLLMs that exploits attention sink behaviors to trigger hallucinated content with minimal image-text relevance.
• Score: 22.781487074263957
• License:
• Abstract: Fusing visual understanding into language generation, Multi-modal Large Language Models (MLLMs) are revolutionizing visual-language applications. Yet, these models are often plagued by the hallucination problem, which involves generating inaccurate objects, attributes, and relationships that do not match the visual content. In this work, we delve into the internal attention mechanisms of MLLMs to reveal the underlying causes of hallucination, exposing the inherent vulnerabilities in the instruction-tuning process. We propose a novel hallucination attack against MLLMs that exploits attention sink behaviors to trigger hallucinated content with minimal image-text relevance, posing a significant threat to critical downstream applications. Distinguished from previous adversarial methods that rely on fixed patterns, our approach generates dynamic, effective, and highly transferable visual adversarial inputs, without sacrificing the quality of model responses. Comprehensive experiments on 6 prominent MLLMs demonstrate the efficacy of our attack in compromising black-box MLLMs even with extensive mitigating mechanisms, as well as the promising results against cutting-edge commercial APIs, such as GPT-4o and Gemini 1.5. Our code is available at https://huggingface.co/RachelHGF/Mirage-in-the-Eyes.

Related papers

• Mitigating Hallucination for Large Vision Language Model by Inter-Modality Correlation Calibration Decoding [66.06337890279839]
  Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding for downstream multi-modal tasks. LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content. We propose an Inter-Modality Correlation Decoding (IMCCD) method to mitigate hallucinations in LVLMs in a training-free manner.
  arXiv  Detail & Related papers  (2025-01-03T17:56:28Z)
• Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence [69.86946427928511]
  We investigate the internal mechanisms driving hallucination in large vision-language models (LVLMs) We introduce Vision-aware Head Divergence (VHD), a metric that quantifies the sensitivity of attention head outputs to visual context. We propose Vision-aware Head Reinforcement (VHR), a training-free approach to mitigate hallucination by enhancing the role of vision-aware attention heads.
  arXiv  Detail & Related papers  (2024-12-18T15:29:30Z)
• Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoning [151.4060202671114]
  multimodal large language models (MLLMs) have shown unprecedented capabilities in advancing vision-language tasks. This paper introduces a novel bottom-up reasoning framework to address hallucinations in MLLMs. Our framework systematically addresses potential issues in both visual and textual inputs by verifying and integrating perception-level information with cognition-level commonsense knowledge.
  arXiv  Detail & Related papers  (2024-12-15T09:10:46Z)
• Reducing Hallucinations in Vision-Language Models via Latent Space Steering [34.1755878632361]
  Hallucination poses a challenge to the deployment of large vision-language models (LVLMs) in applications. We introduce Visual and Textual Intervention (VTI), a novel technique designed to reduce hallucinations by steering latent space representations during inference to enhance the stability of vision features.
  arXiv  Detail & Related papers  (2024-10-21T08:42:30Z)
• MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation [50.73561815838431]
  Multimodal Large Language Models (MLLMs) frequently exhibit hallucination phenomena. We propose a novel dynamic correction decoding method for MLLMs (DeCo) We evaluate DeCo on widely-used benchmarks, demonstrating that it can reduce hallucination rates by a large margin compared to baselines.
  arXiv  Detail & Related papers  (2024-10-15T16:57:44Z)
• From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models [15.401221354325672]
  Hallucinations in large vision models (LVLMs) are a significant challenge, i.e., generating objects that are not presented in the visual input. Recent studies often attribute hallucinations to a lack of understanding of visual input, yet ignore a more fundamental issue: the model's inability to extract or decouple visual features. In this paper, we revisit the hallucinations in LVLMs from an architectural perspective, investigating whether the primary cause lies in the visual encoder (feature extraction) or the modal alignment module (feature decoupling)
  arXiv  Detail & Related papers  (2024-10-09T11:46:32Z)
• DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination [11.845711223575462]
  We find that the attention distribution of Large Language Model (LLM) decoder on image tokens is highly consistent with the visual encoder. We propose DAMRO, a novel training-free strategy that $D$ive into $A$ttention $M$echanism of LVLM.
  arXiv  Detail & Related papers  (2024-10-06T15:12:09Z)
• ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models [11.75855265467876]
  We introduce ConVis, a training-free contrastive decoding method. Our experiments on five popular benchmarks demonstrate that ConVis effectively reduces hallucinations across various MLLMs.
  arXiv  Detail & Related papers  (2024-08-25T18:02:36Z)
• Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback [40.930238150365795]
  We propose detecting and mitigating hallucinations in Large Vision Language Models (LVLMs) via fine-grained AI feedback. We generate a small-size hallucination annotation dataset by proprietary models. Then, we propose a detect-then-rewrite pipeline to automatically construct preference dataset for training hallucination mitigating model.
  arXiv  Detail & Related papers  (2024-04-22T14:46:10Z)
• Hallucination Augmented Contrastive Learning for Multimodal Large Language Model [53.65682783591723]
  Multi-modal large language models (MLLMs) have been shown to efficiently integrate natural language with visual information to handle multi-modal tasks. However, MLLMs still face a fundamental limitation of hallucinations, where they tend to generate erroneous or fabricated information. In this paper, we address hallucinations in MLLMs from a novel perspective of representation learning.
  arXiv  Detail & Related papers  (2023-12-12T04:05:15Z)
• Evaluating Object Hallucination in Large Vision-Language Models [122.40337582958453]
  This work presents the first systematic study on object hallucination of large vision-language models (LVLMs) We find that LVLMs tend to generate objects that are inconsistent with the target images in the descriptions. We propose a polling-based query method called POPE to evaluate the object hallucination.
  arXiv  Detail & Related papers  (2023-05-17T16:34:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.