Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

• URL: http://arxiv.org/abs/2411.18000v2
• Date: Thu, 28 Nov 2024 02:19:55 GMT
• Title: Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models
• Authors: Shuyang Hao, Bryan Hooi, Jun Liu, Kai-Wei Chang, Zi Huang, Yujun Cai,
• Abstract summary: Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues. We introduce MLAI, a novel jailbreak framework that leverages scenario-aware image generation for semantic alignment. Extensive experiments demonstrate MLAI's significant impact, achieving attack success rates of 77.75% on MiniGPT-4 and 82.80% on LLaVA-2.
• Score: 92.79804303337522
• License:
• Abstract: Despite inheriting security measures from underlying language models, Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues. Through empirical analysis, we uncover two critical findings: scenario-matched images can significantly amplify harmful outputs, and contrary to common assumptions in gradient-based attacks, minimal loss values do not guarantee optimal attack effectiveness. Building on these insights, we introduce MLAI (Multi-Loss Adversarial Images), a novel jailbreak framework that leverages scenario-aware image generation for semantic alignment, exploits flat minima theory for robust adversarial image selection, and employs multi-image collaborative attacks for enhanced effectiveness. Extensive experiments demonstrate MLAI's significant impact, achieving attack success rates of 77.75% on MiniGPT-4 and 82.80% on LLaVA-2, substantially outperforming existing methods by margins of 34.37% and 12.77% respectively. Furthermore, MLAI shows considerable transferability to commercial black-box VLMs, achieving up to 60.11% success rate. Our work reveals fundamental visual vulnerabilities in current VLMs safety mechanisms and underscores the need for stronger defenses. Warning: This paper contains potentially harmful example text.

Related papers

• Effective Black-Box Multi-Faceted Attacks Breach Vision Large Language Model Guardrails [32.627286570942445]
  MultiFaceted Attack is an attack framework designed to bypass Multi-Layered Defenses in Vision Large Language Models. It exploits the multimodal nature of VLLMs to inject toxic system prompts through images. It achieves a 61.56% attack success rate, surpassing state-of-the-art methods by at least 42.18%.
  arXiv  Detail & Related papers  (2025-02-09T04:21:27Z)
• Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update [8.739132798784777]
  Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content. We propose an textbfinternal activation revision approach that efficiently revises activations during generation. Our framework incorporates revisions at both the layer and head levels, offering control over the model's generation at varying levels of granularity.
  arXiv  Detail & Related papers  (2025-01-24T06:17:22Z)
• Retention Score: Quantifying Jailbreak Risks for Vision Language Models [60.48306899271866]
  Vision-Language Models (VLMs) are integrated with Large Language Models (LLMs) to enhance multi-modal machine learning capabilities. This paper aims to assess the resilience of VLMs against jailbreak attacks that can compromise model safety compliance and result in harmful outputs. To evaluate a VLM's ability to maintain its robustness against adversarial input perturbations, we propose a novel metric called the textbfRetention Score.
  arXiv  Detail & Related papers  (2024-12-23T13:05:51Z)
• AnyAttack: Targeted Adversarial Attacks on Vision-Language Models toward Any Images [41.044385916368455]
  We propose AnyAttack, a self-supervised framework that generates targeted adversarial images for Vision-Language Models without label supervision. Our framework employs the pre-training and fine-tuning paradigm, with the adversarial noise generator pre-trained on the large-scale LAION-400M dataset.
  arXiv  Detail & Related papers  (2024-10-07T09:45:18Z)
• MirrorCheck: Efficient Adversarial Defense for Vision-Language Models [55.73581212134293]
  We propose a novel, yet elegantly simple approach for detecting adversarial samples in Vision-Language Models. Our method leverages Text-to-Image (T2I) models to generate images based on captions produced by target VLMs. Empirical evaluations conducted on different datasets validate the efficacy of our approach.
  arXiv  Detail & Related papers  (2024-06-13T15:55:04Z)
• White-box Multimodal Jailbreaks Against Large Vision-Language Models [61.97578116584653]
  We propose a more comprehensive strategy that jointly attacks both text and image modalities to exploit a broader spectrum of vulnerability within Large Vision-Language Models. Our attack method begins by optimizing an adversarial image prefix from random noise to generate diverse harmful responses in the absence of text input. An adversarial text suffix is integrated and co-optimized with the adversarial image prefix to maximize the probability of eliciting affirmative responses to various harmful instructions.
  arXiv  Detail & Related papers  (2024-05-28T07:13:30Z)
• Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models [107.88745040504887]
  We study the harmlessness alignment problem of multimodal large language models (MLLMs) Inspired by this, we propose a novel jailbreak method named HADES, which hides and amplifies the harmfulness of the malicious intent within the text input. Experimental results show that HADES can effectively jailbreak existing MLLMs, which achieves an average Attack Success Rate (ASR) of 90.26% for LLaVA-1.5 and 71.60% for Gemini Pro Vision.
  arXiv  Detail & Related papers  (2024-03-14T18:24:55Z)
• On Evaluating Adversarial Robustness of Large Vision-Language Models [64.66104342002882]
  We evaluate the robustness of large vision-language models (VLMs) in the most realistic and high-risk setting. In particular, we first craft targeted adversarial examples against pretrained models such as CLIP and BLIP. Black-box queries on these VLMs can further improve the effectiveness of targeted evasion.
  arXiv  Detail & Related papers  (2023-05-26T13:49:44Z)

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.