Do Multimodal RAG Systems Leak Data? A Comprehensive Evaluation of Membership Inference and Image Caption Retrieval Attacks
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
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+4Lost in Modality: Evaluating the Effectiveness of Text-Based Membership Inference Attacks on Large Multimodal Models
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
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 CaptioningMedQASafe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety
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
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…