通过对抗性域对齐的医学多模态模型窃取攻击
Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment
AI总结：
本文提出首个针对医学多模态大语言模型的窃取攻击ADA-STEAL，通过对抗性噪声增强自然图像以弥合与医学领域的数据分布差距，在无需访问医学数据的情况下成功窃取模型功能。
摘要：
医学多模态大语言模型（MLLMs）正成为医疗系统中不可或缺的一部分，协助医务人员进行决策和结果分析。用于放射学报告生成的模型能够解读医学影像，从而减轻放射科医生的工作负担。由于医学数据稀缺且受隐私法规保护，医学MLLMs代表有价值的知识产权。然而，这些资产可能容易受到模型窃取的攻击，攻击者旨在通过黑盒访问复制其功能。迄今为止，医学领域的模型窃取主要集中于分类任务；然而，现有攻击对MLLMs并不有效。在本文中，我们提出了Adversarial Domain Alignment（ADA-STEAL），这是首个针对医学MLLMs的窃取攻击。ADA-STEAL依赖自然图像，这些图像公开且广泛可用，与医学图像不同。我们表明，使用对抗性噪声进行数据增强足以克服自然图像与受害者MLLM的领域特定分布之间的数据分布差距。在IU X-RAY和MIMIC-CXR放射学数据集上的实验表明，Adversarial Domain Alignment使攻击者能够在没有任何医学数据访问权限的情况下窃取医学MLLM。
英文摘要：
Medical multimodal large language models (MLLMs) are becoming an instrumental part of healthcare systems, assisting medical personnel with decision making and results analysis. Models for radiology report generation are able to interpret medical imagery, thus reducing the workload of radiologists. As medical data is scarce and protected by privacy regulations, medical MLLMs represent valuable intellectual property. However, these assets are potentially vulnerable to model stealing, where attackers aim to replicate their functionality via black-box access. So far, model stealing for the medical domain has focused on classification; however, existing attacks are not effective against MLLMs. In this paper, we introduce Adversarial Domain Alignment (ADA-STEAL), the first stealing attack against medical MLLMs. ADA-STEAL relies on natural images, which are public and widely available, as opposed to their medical counterparts. We show that data augmentation with adversarial noise is sufficient to overcome the data distribution gap between natural images and the domain-specific distribution of the victim MLLM. Experiments on the IU X-RAY and MIMIC-CXR radiology datasets demonstrate that Adversarial Domain Alignment enables attackers to steal the medical MLLM without any access to medical data.
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。
