大视觉语言模型攻击研究综述：资源、进展与未来趋势
A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends
AI总结：
该综述系统梳理了大视觉语言模型（LVLMs）的攻击研究背景、四类主流攻击方法及相关资源，探讨了未来研究方向，为LVLM安全研究提供参考并推动相关安全问题的缓解。
摘要：
近年来，随着大模型的显著发展，大视觉语言模型（Large Vision-Language Models, LVLMs）已在广泛的多模态理解与推理任务中展现出卓越能力。与传统大语言模型（Large Language Models, LLMs）相比，LVLMs因更贴近多资源的现实世界应用场景，且多模态处理过程更为复杂，既具备巨大潜力也带来了诸多挑战。然而，目前学界对LVLMs的脆弱性探索相对不足，这给其日常使用埋下了潜在安全风险。\n本文对现有各类LVLM攻击形式展开了全面综述。具体而言，我们首先介绍了针对LVLMs的攻击研究背景，涵盖攻击基础、攻击挑战以及攻击资源。随后，我们系统梳理了LVLM攻击方法的发展脉络，包括操纵模型输出的对抗攻击、利用模型漏洞执行未授权操作的越狱攻击、设计提示类型与模式的提示注入攻击，以及影响模型训练的数据投毒攻击。最后，我们探讨了未来值得探索的研究方向。我们认为本综述清晰呈现了当前LVLM脆弱性的研究现状，能够启发更多研究者探索并缓解LVLM发展过程中的潜在安全问题。最新的LVLM攻击相关论文会持续收录于https://github.com/liudaizong/Awesome-LVLM-Attack。
英文摘要：
With the significant development of large models in recent years, Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a wide range of multimodal understanding and reasoning tasks. Compared to traditional Large Language Models (LLMs), LVLMs present great potential and challenges due to its closer proximity to the multi-resource real-world applications and the complexity of multi-modal processing. However, the vulnerability of LVLMs is relatively underexplored, posing potential security risks in daily usage. In this paper, we provide a comprehensive review of the various forms of existing LVLM attacks. Specifically, we first introduce the background of attacks targeting LVLMs, including the attack preliminary, attack challenges, and attack resources. Then, we systematically review the development of LVLM attack methods, such as adversarial attacks that manipulate model outputs, jailbreak attacks that exploit model vulnerabilities for unauthorized actions, prompt injection attacks that engineer the prompt type and pattern, and data poisoning that affects model training. Finally, we discuss promising research directions in the future. We believe that our survey provides insights into the current landscape of LVLM vulnerabilities, inspiring more researchers to explore and mitigate potential safety issues in LVLM developments. The latest papers on LVLM attacks are continuously collected in https://github.com/liudaizong/Awesome-LVLM-Attack.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
