Transferable Adversarial Attacks on Black-Box Vision-Language Models

• URL: http://arxiv.org/abs/2505.01050v1
• Date: Fri, 02 May 2025 06:51:11 GMT
• Title: Transferable Adversarial Attacks on Black-Box Vision-Language Models
• Authors: Kai Hu, Weichen Yu, Li Zhang, Alexander Robey, Andy Zou, Chengming Xu, Haoqi Hu, Matt Fredrikson,
• Abstract summary: adversarial attacks can transfer from open-source to proprietary black-box models in text-only and vision-only contexts.<n>We show that attackers can craft perturbations to induce specific attacker-chosen interpretations of visual information.<n>We discover that universal perturbations -- modifications applicable to a wide set of images -- can consistently induce these misinterpretations.
• Score: 63.22532779621001
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Large Language Models (VLLMs) are increasingly deployed to offer advanced capabilities on inputs comprising both text and images. While prior research has shown that adversarial attacks can transfer from open-source to proprietary black-box models in text-only and vision-only contexts, the extent and effectiveness of such vulnerabilities remain underexplored for VLLMs. We present a comprehensive analysis demonstrating that targeted adversarial examples are highly transferable to widely-used proprietary VLLMs such as GPT-4o, Claude, and Gemini. We show that attackers can craft perturbations to induce specific attacker-chosen interpretations of visual information, such as misinterpreting hazardous content as safe, overlooking sensitive or restricted material, or generating detailed incorrect responses aligned with the attacker's intent. Furthermore, we discover that universal perturbations -- modifications applicable to a wide set of images -- can consistently induce these misinterpretations across multiple proprietary VLLMs. Our experimental results on object recognition, visual question answering, and image captioning show that this vulnerability is common across current state-of-the-art models, and underscore an urgent need for robust mitigations to ensure the safe and secure deployment of VLLMs.

Related papers

• VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models [15.158545794377169]
  We frame the preservation of privacy in Vision-Language Models as an adversarial attack problem.<n>We propose a novel attack strategy that selectively conceals information within designated Region Of Interests in an image.<n> Experimental results across three state-of-the-art VLMs demonstrate up to 98% reduction in detecting targeted ROIs.
  arXiv  Detail & Related papers  (2025-07-11T19:34:01Z)
• Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models [92.79804303337522]
  Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues.<n>We introduce MLAI, a novel jailbreak framework that leverages scenario-aware image generation for semantic alignment.<n>Extensive experiments demonstrate MLAI's significant impact, achieving attack success rates of 77.75% on MiniGPT-4 and 82.80% on LLaVA-2.
  arXiv  Detail & Related papers  (2024-11-27T02:40:29Z)
• Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models [15.029014337718849]
  Large vision-language models (LVLMs) integrate visual information into large language models, showcasing remarkable multi-modal conversational capabilities. In general, LVLMs rely on vision encoders to transform images into visual tokens, which are crucial for the language models to perceive image contents effectively. We propose a non-targeted attack method referred to as VT-Attack, which constructs adversarial examples from multiple perspectives.
  arXiv  Detail & Related papers  (2024-10-09T09:06:56Z)
• AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models [39.34959092321762]
  Vision-Language Models (VLMs) are vulnerable to image-based adversarial attacks.<n>We present AnyAttack, a self-supervised framework that transcends the limitations of conventional attacks.
  arXiv  Detail & Related papers  (2024-10-07T09:45:18Z)
• Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors [31.383591942592467]
  Vision-language models (VLMs) offer innovative ways to combine visual and textual data for enhanced understanding and interaction. Patch-based adversarial attack is considered the most realistic threat model in physical vision applications. We introduce SmoothVLM, a defense mechanism rooted in smoothing techniques, to protectVLMs from the threat of patched visual prompt injectors.
  arXiv  Detail & Related papers  (2024-05-17T04:19:19Z)
• SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation [56.622250514119294]
  In contrast to white-box adversarial attacks, transfer attacks are more reflective of real-world scenarios. We propose a self-augment-based transfer attack method, termed SA-Attack.
  arXiv  Detail & Related papers  (2023-12-08T09:08:50Z)
• Adversarial Prompt Tuning for Vision-Language Models [86.5543597406173]
  Adversarial Prompt Tuning (AdvPT) is a technique to enhance the adversarial robustness of image encoders in Vision-Language Models (VLMs) We demonstrate that AdvPT improves resistance against white-box and black-box adversarial attacks and exhibits a synergistic effect when combined with existing image-processing-based defense techniques.
  arXiv  Detail & Related papers  (2023-11-19T07:47:43Z)
• Visual Adversarial Examples Jailbreak Aligned Large Language Models [66.53468356460365]
  We show that the continuous and high-dimensional nature of the visual input makes it a weak link against adversarial attacks. We exploit visual adversarial examples to circumvent the safety guardrail of aligned LLMs with integrated vision. Our study underscores the escalating adversarial risks associated with the pursuit of multimodality.
  arXiv  Detail & Related papers  (2023-06-22T22:13:03Z)
• 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.