多維度攻擊：揭示具備防禦機制視覺語言模型的跨模型漏洞

摘要

随着视觉语言模型（VLMs）的滥用日益严重，服务商已部署包括对齐调优、系统提示和内容审核在内的多重防护机制。然而，这些防御措施在面对对抗攻击时的实际鲁棒性仍有待深入探究。本文提出多维度攻击框架（MFA），通过系统化测试揭示GPT-4o、Gemini-Pro和Llama-4等主流防护型VLM的通用安全漏洞。MFA的核心组件是注意力转移攻击（ATA），该技术将恶意指令隐藏于具有竞争目标的元任务中。基于奖励破解理论，我们为攻击成功提供了理论解释。为提升跨模型迁移性，我们进一步结合轻量级迁移增强算法与简单重复策略，无需模型特定微调即可协同绕过输入级与输出级过滤器。实证研究表明，针对某一视觉编码器优化的对抗图像可广泛迁移至未见过的VLM，表明共享视觉表征会引发跨模型安全漏洞。总体而言，MFA实现了58.5%的成功率，持续优于现有方法。在最新商用模型上，MFA达到52.8%的成功率，较次优攻击方法提升34%。这些结果挑战了现有防御机制的感知鲁棒性，并揭示现代VLM持续存在的安全缺陷。代码地址：https://github.com/cure-lab/MultiFacetedAttack

English

The growing misuse of Vision-Language Models (VLMs) has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and content moderation. However, the real-world robustness of these defenses against adversarial attacks remains underexplored. We introduce Multi-Faceted Attack (MFA), a framework that systematically exposes general safety vulnerabilities in leading defense-equipped VLMs such as GPT-4o, Gemini-Pro, and Llama-4. The core component of MFA is the Attention-Transfer Attack (ATA), which hides harmful instructions inside a meta task with competing objectives. We provide a theoretical perspective based on reward hacking to explain why this attack succeeds. To improve cross-model transferability, we further introduce a lightweight transfer-enhancement algorithm combined with a simple repetition strategy that jointly bypasses both input-level and output-level filters without model-specific fine-tuning. Empirically, we show that adversarial images optimized for one vision encoder transfer broadly to unseen VLMs, indicating that shared visual representations create a cross-model safety vulnerability. Overall, MFA achieves a 58.5% success rate and consistently outperforms existing methods. On state-of-the-art commercial models, MFA reaches a 52.8% success rate, surpassing the second-best attack by 34%. These results challenge the perceived robustness of current defense mechanisms and highlight persistent safety weaknesses in modern VLMs. Code: https://github.com/cure-lab/MultiFacetedAttack

多維度攻擊：揭示具備防禦機制視覺語言模型的跨模型漏洞

Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models

摘要

Support