AnyAttack: Targeted Adversarial Attacks on Vision-Language Models toward Any Images

• URL: http://arxiv.org/abs/2410.05346v2
• Date: Tue, 17 Dec 2024 15:32:04 GMT
• Title: AnyAttack: Targeted Adversarial Attacks on Vision-Language Models toward Any Images
• Authors: Jiaming Zhang, Junhong Ye, Xingjun Ma, Yige Li, Yunfan Yang, Jitao Sang, Dit-Yan Yeung,
• Abstract summary: 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.
• Score: 41.044385916368455
• License:
• Abstract: Due to their multimodal capabilities, Vision-Language Models (VLMs) have found numerous impactful applications in real-world scenarios. However, recent studies have revealed that VLMs are vulnerable to image-based adversarial attacks, particularly targeted adversarial images that manipulate the model to generate harmful content specified by the adversary. Current attack methods rely on predefined target labels to create targeted adversarial attacks, which limits their scalability and applicability for large-scale robustness evaluations. In this paper, we propose AnyAttack, a self-supervised framework that generates targeted adversarial images for VLMs without label supervision, allowing any image to serve as a target for the attack. Our framework employs the pre-training and fine-tuning paradigm, with the adversarial noise generator pre-trained on the large-scale LAION-400M dataset. This large-scale pre-training endows our method with powerful transferability across a wide range of VLMs. Extensive experiments on five mainstream open-source VLMs (CLIP, BLIP, BLIP2, InstructBLIP, and MiniGPT-4) across three multimodal tasks (image-text retrieval, multimodal classification, and image captioning) demonstrate the effectiveness of our attack. Additionally, we successfully transfer AnyAttack to multiple commercial VLMs, including Google Gemini, Claude Sonnet, Microsoft Copilot and OpenAI GPT. These results reveal an unprecedented risk to VLMs, highlighting the need for effective countermeasures.

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)
• 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. 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.
  arXiv  Detail & Related papers  (2024-11-27T02:40:29Z)
• 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)
• Adversarial Robustness for Visual Grounding of Multimodal Large Language Models [49.71757071535619]
  Multi-modal Large Language Models (MLLMs) have recently achieved enhanced performance across various vision-language tasks. adversarial robustness of visual grounding remains unexplored in MLLMs. We propose three adversarial attack paradigms as follows.
  arXiv  Detail & Related papers  (2024-05-16T10:54:26Z)
• Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective [42.04728834962863]
  Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. Recent studies reveal their vulnerability to adversarial attacks, with defenses against text-based and multimodal attacks remaining largely unexplored. This work presents the first comprehensive study on improving the adversarial robustness of VLMs against attacks targeting image, text, and multimodal inputs.
  arXiv  Detail & Related papers  (2024-04-30T06:34:21Z)
• VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models [65.23688155159398]
  Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. Adversaries can implant a backdoor by injecting poisoned samples with triggers embedded in instructions or images. We propose a multimodal instruction backdoor attack, namely VL-Trojan.
  arXiv  Detail & Related papers  (2024-02-21T14:54:30Z)
• VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models [46.14455492739906]
  Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. Existing approaches mainly focus on exploring the adversarial robustness under the white-box setting. We propose VLATTACK to generate adversarial samples by fusing perturbations of images and texts from both single-modal and multimodal levels.
  arXiv  Detail & Related papers  (2023-10-07T02:18:52Z)
• 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.