mlsanityData to 7 Oct 2026

Membership Inference Attacks against Large Vision-Language Models

arXiv 2411.02902 ↗First posted 5 Nov 2024cs.CV cs.AI cs.CLcited by 31

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

also in 1 more
Abstract (arXiv)

Large vision-language models (VLLMs) exhibit promising capabilities for processing multi-modal tasks across various application scenarios. However, their emergence also raises significant data security concerns, given the potential inclusion of sensitive information, such as private photos and medical records, in their training datasets. Detecting inappropriately used data in VLLMs remains a critical and unresolved issue, mainly due to the lack of standardized datasets and suitable methodologies. In this study, we introduce the first membership inference attack (MIA) benchmark tailored for various VLLMs to facilitate training data detection. Then, we propose a novel MIA pipeline specifically designed for token-level image detection. Lastly, we present a new metric called MaxR'enyi-K%, which is based on the confidence of the model output and applies to both text and image data. We believe that our work can deepen the understanding and methodology of MIAs in the context of VLLMs. Our code and datasets are available at https://github.com/LIONS-EPFL/VL-MIA.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 44 of its 65 references that are in the map. First posted on arXiv 5 Nov 2024.

Builds on

44 of 65 references.

References · 44

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2023Visual Instruction Tuningcited by 7,792
  6. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  8. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  9. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  10. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  11. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  12. 2020Extracting Training Data from Large Language Modelscited by 2,144
32 more
  1. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  2. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  3. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  4. 2021Membership Inference Attacks From First Principlescited by 839
  5. 2023LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attentioncited by 776
  6. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 617
  7. 2023LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Modelcited by 602
  8. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  9. 2023Detecting Pretraining Data from Large Language Modelscited by 375
  10. 2020Label-Only Membership Inference Attackscited by 371
  11. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 359
  12. 2022Deduplicating Training Data Mitigates Privacy Risks in Language Modelscited by 309
  13. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  14. 2023InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Compositioncited by 297
  15. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  16. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 237
  17. 2023Proving Test Set Contamination in Black Box Language Modelscited by 227
  18. 2020Information Leakage in Embedding Modelscited by 199
  19. 2024Do Membership Inference Attacks Work on Large Language Models?cited by 188
  20. 2023Time Travel in LLMs: Tracing Data Contamination in Large Language Modelscited by 175
  21. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 168
  22. 2017Machine Learning Models that Remember Too Muchcited by 165
  23. 2023BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questionscited by 125
  24. 2019Reconstruction and Membership Inference Attacks against Generative Modelscited by 122
  25. 2023Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Modelscited by 100
  26. 2023Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibrationcited by 90
  27. 2018Understanding Membership Inferences on Well-Generalized Learning Modelscited by 83
  28. 2021EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learningcited by 68
  29. 2024Blind Baselines Beat Membership Inference Attacks for Foundation Modelscited by 65
  30. 2023Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Studycited by 37
  31. 2021Membership Inference on Word Embedding and Beyondcited by 34
  32. 2022M^4I: Multi-modal Models Membership Inferencecited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 18; 2026: 13.

31 papers.

Sort:

By area:

  1. 2025Discrete Diffusion in Large Language and Multimodal Models: A Surveycited by 61
  2. 2025Membership Inference Attacks on Large-Scale Models: A Surveycited by 17
  3. 2025Vid-SME: Membership Inference Attacks against Large Video Understanding Modelscited by 17
  4. 2025When Continue Learning Meets Multimodal Large Language Model: A Surveycited by 8
  5. 2025ICAS: Detecting Training Data from Autoregressive Image Generative Modelscited by 6
  6. 2025Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Modelscited by 5
  7. 2025Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Modelscited by 4
  8. 2025SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controllingcited by 3
  9. 2025Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probingcited by 3
  10. 2025In-Context Probing for Membership Inference in Fine-Tuned Language Modelscited by 3
  11. 2025How does Bayesian Sampling help Membership Inference Attacks?cited by 2
  12. 2025MrM: Black-Box Membership Inference Attacks against Multimodal RAG Systemscited by 2
19 more
  1. 2025Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?cited by 2
  2. 2026VLALeaks: Membership Inference Attacks against Vision-Language-Action Modelscited by 2
  3. 2025DIS-CO: Discovering Copyrighted Content in VLMs Training Datacited by 1
  4. 2025FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updatescited by 1
  5. 2025Provable Training Data Identification for Large Language Modelscited by 1
  6. 2025OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Modelscited by 1
  7. 2026Membership Inference Attacks against Large Audio Language Modelscited by 1
  8. 2025Lost in Modality: Evaluating the Effectiveness of Text-Based Membership Inference Attacks on Large Multimodal Modelscited by 0
  9. 2026Text is All You Need for Vision-Language Model Jailbreakingcited by 0
  10. 2026AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Explorationcited by 0
  11. 2026Position: Life-Logging Video Streams Make the Privacy-Utility Trade-off Inevitablecited by 0
  12. 2026DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distractioncited by 0
  13. 2026Single-Sample Black-Box Membership Inference Attack against Vision-Language Models via Cross-modal Semantic Alignmentcited by 0
  14. 2026Provable Joint Decontamination for Benchmarking Multiple Large Language Modelscited by 0
  15. 2026Revealing Training Data Exposure in Vision Language Large Models via Parameter Gradientscited by 0
  16. 2026One Framework for All: Cross-Modal Membership Inference for Generative Modelscited by 0
  17. 2026MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data Poisoningcited by 0
  18. 2026DIME: Query-Efficient Framework for Membership Inference on Diffusion Modelscited by 0
  19. 2026Position: Privacy Is a Claim, Not a Property of Synthetic Datacited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models
  2. 2025Membership Inference Attacks Against Vision-Language Models
  3. 2024Self-Comparison for Dataset-Level Membership Inference in Large (Vision-)Language Models
  4. 2025Revisiting Data Auditing in Large Vision-Language Models
  5. 2026Detecting Data Contamination in Large Language Models
  6. 2024A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends
  7. 2024Backdooring Vision-Language Models with Out-Of-Distribution Data
  8. 2025FiMMIA: scaling semantic perturbation-based membership inference across modalities