Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Al-Lawati, Ali, Wang, Suhang
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM Benchmark Datasets Should Be Contamination-Resistant
by: Al-Lawati, Ali, et al.
Published: (2026)

E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems
by: Guan, Zelin, et al.
Published: (2026)

Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation
by: Li, Yuying, et al.
Published: (2024)

Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries
by: Wang, Yuhao, et al.
Published: (2025)

LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models
by: Ran, Delong, et al.
Published: (2025)

Lost in Modality: Evaluating the Effectiveness of Text-Based Membership Inference Attacks on Large Multimodal Models
by: Tong, Ziyi, et al.
Published: (2025)

BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channel
by: Li, Hao, et al.
Published: (2025)

Mask-based Membership Inference Attacks for Retrieval-Augmented Generation
by: Liu, Mingrui, et al.
Published: (2024)

MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Data
by: German, Eyal, et al.
Published: (2025)

Membership Inference Attacks on Recommender System: A Survey
by: He, Jiajie, et al.
Published: (2025)

Membership Inference Attacks Against Vision-Language Models
by: Hu, Yuke, et al.
Published: (2025)

Membership Inference Attacks on Tokenizers of Large Language Models
by: Tong, Meng, et al.
Published: (2025)

Membership Inference Attack with Partial Features
by: Wang, Xurun, et al.
Published: (2025)

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
by: Zhang, Kaiyuan, et al.
Published: (2025)

DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation
by: Gao, Xinyu, et al.
Published: (2025)

P-MIA: A Profiled-Based Membership Inference Attack on Cognitive Diagnosis Models
by: Hou, Mingliang, et al.
Published: (2025)

On Membership Inference Attacks in Knowledge Distillation
by: Cui, Ziyao, et al.
Published: (2025)

Biologically-Informed Hybrid Membership Inference Attacks on Generative Genomic Models
by: Belfiore, Asia, et al.
Published: (2025)

Win-k: Improved Membership Inference Attacks on Small Language Models
by: Arkhmammadova, Roya, et al.
Published: (2025)

LeakDojo: Decoding the Leakage Threats of RAG Systems
by: Zhang, Maosen, et al.
Published: (2026)

Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
by: Yin, Jinhua, et al.
Published: (2025)

Ensemble Privacy Defense for Knowledge-Intensive LLMs against Membership Inference Attacks
by: Fu, Haowei, et al.
Published: (2025)

Learning-Based Difficulty Calibration for Enhanced Membership Inference Attacks
by: Shi, Haonan, et al.
Published: (2024)

PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization
by: Jiao, Yang, et al.
Published: (2025)

Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack
by: Xue, Jing, et al.
Published: (2025)

LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states
by: Ibanez-Lissen, Luis, et al.
Published: (2024)

Membership Inference Attacks fueled by Few-Short Learning to detect privacy leakage tackling data integrity
by: Jiménez-López, Daniel, et al.
Published: (2025)

Center-Based Relaxed Learning Against Membership Inference Attacks
by: Fang, Xingli, et al.
Published: (2024)

CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning
by: Chen, Depeng, et al.
Published: (2024)

Improved Membership Inference Attacks Against Language Classification Models
by: Shachor, Shlomit, et al.
Published: (2023)

Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis
by: Wu, Xiaoyu, et al.
Published: (2025)

Do Parameters Reveal More than Loss for Membership Inference?
by: Suri, Anshuman, et al.
Published: (2024)

Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking
by: Cohen, Stav, et al.
Published: (2024)

On the Evidentiary Limits of Membership Inference for Copyright Auditing
by: Ertan, Murat Bilgehan, et al.
Published: (2026)

The Hidden Threat in Plain Text: Attacking RAG Data Loaders
by: Castagnaro, Alberto, et al.
Published: (2025)

When Reasoning Leaks Membership: Membership Inference Attack on Black-box Large Reasoning Models
by: Hu, Ruihan, et al.
Published: (2026)

SD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented Generation
by: Masoud, Aiman Al, et al.
Published: (2026)

Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey
by: Jain, Bhavuk, et al.
Published: (2026)

Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation
by: Anderson, Maya, et al.
Published: (2024)

Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy
by: Sui, Zhihao, et al.
Published: (2025)