Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information. However, Multi-modal Large Language Models (MLLMs), which process both text and images, introduce unique privacy challenges that remain underexplored. Compared to text-only models, MLLMs can extract and expose sensitive information embedded in images, posing new privacy risks. We reveal that some MLLMs are susceptible to privacy breaches, leaking sensitive data embedded in images or stored in memory. Specifically, in this paper, we (1) introduce MM-Privacy, a comprehensive dataset designed to assess privacy risks across various multi-modal tasks and scenarios, where we define Disclosure Risks and Retention Risks. (2) systematically evaluate different MLLMs using MM-Privacy and demonstrate how models leak sensitive data across various tasks, and (3) provide additional insights into the role of task inconsistency in privacy risks, emphasizing the urgent need for mitigation strategies. Our findings highlight privacy concerns in MLLMs, underscoring the necessity of safeguards to prevent data exposure. Our dataset and code can be found here.

翻译：文本型大语言模型（LLM）的隐私风险已得到充分研究，特别是其记忆和泄露敏感信息的倾向。然而，可同时处理文本与图像的多模态大语言模型（MLLM）带来了尚未充分探索的独特隐私挑战。相较于纯文本模型，MLLM能够提取并暴露图像中嵌入的敏感信息，从而引发新的隐私风险。我们揭示部分MLLM存在隐私泄露漏洞，导致其可能泄露图像中嵌入或存储于记忆中的敏感数据。具体而言，本文：(1) 提出MM-Privacy综合数据集，旨在评估多模态任务与场景中的隐私风险，并定义了"披露风险"与"留存风险"两种类型；(2) 利用MM-Privacy对不同MLLM进行系统评估，展示模型在各任务场景中泄露敏感数据的方式；(3) 进一步揭示任务不一致性对隐私风险的影响，强调制定缓解策略的紧迫性。我们的研究凸显了MLLM中的隐私隐患，亟需建立防护机制以防止数据暴露。数据集与代码已开源。