paper-with-me

홈 › Papers

Do Multimodal RAG Systems Leak Data? A Comprehensive Evaluation of Membership Inference and Image Caption Retrieval Attacks

2026-01-25 · Ali Al-Lawati, Suhang Wang arxiv

The growing adoption of multimodal Retrieval-Augmented Generation (mRAG) pipelines for vision-centric tasks (e.g., visual QA) introduces important privacy challenges. In particular, while mRAG provides a practical capability to connect private datasets and improve model performance, it risks the leakage of private information from these datasets. In this paper, we perform an empirical study to analyze the privacy risks inherent in the mRAG pipeline observed through standard model prompting. Specifically, we implement a case study that attempts to determine whether a visual asset (e.g., image) is included in the mRAG, and, if present, to leak the metadata (e.g., caption) related to it. Our findings highlight the need for privacy-preserving mechanisms and motivate future research on mRAG privacy. Our code is published online: https://github.com/aliwister/mrag-attack-eval.

📄 PDF Abstract BibTeX arXiv:2601.17644

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

2023-06-23 · Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin 외

Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image. However, it is difficult for t…

BenchmarkingLanguage ModelingLanguage ModellingLarge Language Model+4

Lost in Modality: Evaluating the Effectiveness of Text-Based Membership Inference Attacks on Large Multimodal Models

2025-12-02 · Ziyi Tong, Feifei Sun, Le Minh Nguyen arxiv

Large Multimodal Language Models (MLLMs) are emerging as one of the foundational tools in an expanding range of applications. Consequently, understanding training-data leakage in these systems is increasingly critical. L…

MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

2025-01-30 · Yuxin Zuo, Shang Qu, Yifei Li, Zhangren Chen 외

We introduce MedXpertQA, a highly challenging and comprehensive benchmark to evaluate expert-level medical knowledge and advanced reasoning. MedXpertQA includes 4,460 questions spanning 17 specialties and 11 body systems…

BenchmarkingDecision MakingImage CaptioningMedQA

Safe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety

2025-08-29 · Younggun Kim, Sirnam Swetha, Fazil Kagdi, Mubarak Shah arxiv

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks. However, these models often infer and reveal sensitive biometric attributes such as race, gender, age, body wei…

VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering

2026-03-11 · Youting Wang, Yuan Tang, Yitian Qian, Chen Zhao arxiv

As Large Vision-Language Models (LVLMs) are increasingly deployed in agent-integrated workflows and other deployment-relevant settings, their robustness against semantic visual attacks remains under-evaluated -- alignmen…