arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.20168cs.CRcs.AIcs.LG
收藏

奥德赛:通过双隐写术对集成多模态大语言模型系统的商业系统进行劫持

Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography

S3IC-Lab(S3IC实验室)

Songze Li, Jiameng Cheng, Yiming Li, Xiaojun Jia, Dacheng Tao

AI总结:

奥德赛通过双隐写术劫持多模态大语言模型集成系统,揭示现有安全过滤器的局限性,实现高达99%的攻击成功率。

摘要:

通过将语言理解与图像等感知模态相结合,多模态大语言模型(MLLMs)成为现代人工智能系统的关键基础,特别是智能代理在开放和交互环境中运行。然而,其日益增加的可访问性也带来了更高的滥用风险,例如生成有害或不安全的内容。为了缓解这些风险,通常应用对齐技术来使模型行为与人类价值观对齐。尽管这些努力,最近的研究表明,劫持攻击可以绕过对齐并引发不安全的输出。目前,大多数现有的劫持方法都是为开源模型量身定制的,并且在针对集成多模态大语言模型系统的商业系统中效果有限,这些系统通常采用额外的过滤器。这些过滤器可以检测并阻止恶意输入和输出内容,显著降低劫持威胁。在本文中,我们揭示了这些安全过滤器的成功依赖于一个关键假设,即恶意内容必须在输入或输出中显式可见。这个假设虽然在传统LLM集成系统中通常是有效的,但在集成多模态大语言模型系统中会失效,因为攻击者可以利用多种模态来隐藏对抗意图,导致现有多模态大语言模型集成系统产生一种虚假的安全感。为了挑战这一假设,我们提出了奥德赛,一种新的劫持范式,它引入了双隐写术,将恶意查询和响应隐含地嵌入到看似无害的图像中。在基准数据集上的广泛实验表明,我们的奥德赛成功劫持了几个开创性和现实的多模态大语言模型集成系统,达到了高达99%的攻击成功率。它暴露了现有防御中的一个根本性盲点,并呼吁重新思考多模态安全问题。

英文摘要:

By integrating language understanding with perceptual modalities such as images, multimodal large language models (MLLMs) constitute a critical substrate for modern AI systems, particularly intelligent agents operating in open and interactive environments. However, their increasing accessibility also raises heightened risks of misuse, such as generating harmful or unsafe content. To mitigate these risks, alignment techniques are commonly applied to align model behavior with human values. Despite these efforts, recent studies have shown that jailbreak attacks can circumvent alignment and elicit unsafe outputs. Currently, most existing jailbreak methods are tailored for open-source models and exhibit limited effectiveness against commercial MLLM-integrated systems, which often employ additional filters. These filters can detect and prevent malicious input and output content, significantly reducing jailbreak threats. In this paper, we reveal that the success of these safety filters heavily relies on a critical assumption that malicious content must be explicitly visible in either the input or the output. This assumption, while often valid for traditional LLM-integrated systems, breaks down in MLLM-integrated systems, where attackers can leverage multiple modalities to conceal adversarial intent, leading to a false sense of security in existing MLLM-integrated systems. To challenge this assumption, we propose Odysseus, a novel jailbreak paradigm that introduces dual steganography to covertly embed malicious queries and responses into benign-looking images. Extensive experiments on benchmark datasets demonstrate that our Odysseus successfully jailbreaks several pioneering and realistic MLLM-integrated systems, achieving up to 99% attack success rate. It exposes a fundamental blind spot in existing defenses, and calls for rethinking cross-modal security in MLLM-integrated systems.

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。

↑