paper-with-me

Papers

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

2026-06-08 · Tiejin Chen, Pingzhi Li, Kaixiong Zhou, Tianlong Chen, Hua Wei arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.09125

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation

2025-05-20 · Jiankun Zhang, Shenglai Zeng, Jie Ren, Tianqi Zheng 외

Multimodal Retrieval-Augmented Generation (MRAG) systems enhance LMMs by integrating external multimodal databases, but introduce unexplored privacy vulnerabilities. While text-based RAG privacy risks have been studied, …

Privacy PreservingRAGRetrievalRetrieval-augmented Generation

Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation

2025-08-21 · Yichi Zhang, Yao Huang, Yifan Wang, Yitong Sun 외 arxiv

The trustworthiness of Multimodal Large Language Models (MLLMs) remains an intense concern despite the significant progress in their capabilities. Existing evaluation and mitigation approaches often focus on narrow aspec…

Unveiling Privacy Risks in LLM Agent Memory

2025-02-17 · Bo wang, Weiyi He, Shenglai Zeng, Zhen Xiang 외

Large Language Model (LLM) agents have become increasingly prevalent across various real-world applications. They enhance decision-making by storing private user-agent interactions in the memory module for demonstrations…

Decision MakingLanguage ModelingLanguage ModellingLarge Language Model

GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents

2025-11-27 · Xinyu Zhang, Yixin Wu, Boyang Zhang, Chenhao Lin 외 arxiv

Images shared on social media often expose geographic cues. While early geolocation methods required expert effort and lacked generalization, the rise of Large Vision Language Models (LVLMs) now enables accurate geolocat…

Unveiling Security, Privacy, and Ethical Concerns of ChatGPT

2023-07-26 · Xiaodong Wu, Ran Duan, Jianbing Ni

This paper delves into the realm of ChatGPT, an AI-powered chatbot that utilizes topic modeling and reinforcement learning to generate natural responses. Although ChatGPT holds immense promise across various industries, …

ChatbotEthics