2606.09125v1 Jun 08, 2026 cs.CR

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges

Pingzhi Li
Pingzhi Li
Citations: 417
h-index: 9
Tiejin Chen
Tiejin Chen
Citations: 287
h-index: 8
Hua Wei
Hua Wei
Citations: 52
h-index: 3
Kaixiong Zhou
Kaixiong Zhou
Citations: 82
h-index: 5
Tianlong Chen
Tianlong Chen
Citations: 49
h-index: 3

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.

15 Citations
0 Influential
4.5 Altmetric
37.5 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!