arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.00352cs.CV
收藏

面向文本到动作生成的自主大语言模型增强对抗攻击

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

School of Information Science and Engineering, Lanzhou University(兰州大学信息科学与工程学院);CCAI, Zhejiang University(浙江大学CCAI)

Honglei Miao, Fan Ma, Ruijie Quan, Kun Zhan, Yi Yang

AI总结:

本文提出ALERT-Motion框架,利用大语言模型自主生成针对黑盒文本到动作模型的隐蔽对抗攻击,通过自适应调度和多模态对比模块实现更高攻击成功率,并强调防御研究的紧迫性。

摘要:

由深度生成模型驱动的人体动作生成已经催生了引人注目的应用,但文本到动作(T2M)模型从文本提示生成逼真动作的能力,若被恶意利用,将引发安全担忧。尽管对T2M的兴趣日益增长,但很少有方法专注于保护这些模型免受对抗攻击,而现有针对文本到图像模型的研究已被证明不足以应对独特的动作领域。在本文中,我们提出了ALERT-Motion,这是一个利用大语言模型(LLMs)自主构建针对黑盒T2M模型的定向对抗攻击的框架。与先前通过预定义规则修改提示的方法不同,ALERT-Motion利用大语言模型对人体动作的知识,自主生成微妙但强大的对抗性文本描述。它包含两个关键模块:一个自适应调度模块,该模块构建一个基于大语言模型的智能体,以迭代地优化和搜索对抗性提示;以及一个多模态信息对比模块,该模块提取语义相关的动作信息以引导智能体的搜索。通过这种由大语言模型驱动的方法,ALERT-Motion构建对抗性提示来查询受害模型,使其产生与目标动作高度匹配的输出,同时避免明显的扰动。在流行的T2M模型上的评估表明,ALERT-Motion优于先前的方法,以更隐蔽的对抗性提示实现了更高的攻击成功率。这项关于T2M对抗攻击的开创性工作突显了随着动作生成技术的发展,制定防御措施的紧迫性,并敦促进一步研究安全且负责任的部署。

英文摘要:

Human motion generation driven by deep generative models has enabled compelling applications, but the ability of text-to-motion (T2M) models to produce realistic motions from text prompts raises security concerns if exploited maliciously. Despite growing interest in T2M, few methods focus on safeguarding these models against adversarial attacks, with existing work on text-to-image models proving insufficient for the unique motion domain. In the paper, we propose ALERT-Motion, an autonomous framework leveraging large language models (LLMs) to craft targeted adversarial attacks against black-box T2M models. Unlike prior methods modifying prompts through predefined rules, ALERT-Motion uses LLMs' knowledge of human motion to autonomously generate subtle yet powerful adversarial text descriptions. It comprises two key modules: an adaptive dispatching module that constructs an LLM-based agent to iteratively refine and search for adversarial prompts; and a multimodal information contrastive module that extracts semantically relevant motion information to guide the agent's search. Through this LLM-driven approach, ALERT-Motion crafts adversarial prompts querying victim models to produce outputs closely matching targeted motions, while avoiding obvious perturbations. Evaluations across popular T2M models demonstrate ALERT-Motion's superiority over previous methods, achieving higher attack success rates with stealthier adversarial prompts. This pioneering work on T2M adversarial attacks highlights the urgency of developing defensive measures as motion generation technology advances, urging further research into safe and responsible deployment.

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。

↑