mlsanityData to 14 Oct 2026

Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models

arXiv 2506.12340 ↗First posted 14 Jun 2025cs.CV cs.CRcited by 3

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

also in 1 more
Abstract (arXiv)

Large vision-language models (LVLMs) have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy risks if training images contain sensitive information. Therefore, it is important to detect whether an image is used to train the LVLM. Recent studies have investigated membership inference attacks (MIAs) against LVLMs, including detecting image-text pairs and single-modality content. In this work, we focus on detecting whether a target image is used to train the target LVLM. We design simple yet effective Image Corruption-Inspired Membership Inference Attacks (ICIMIA) against LVLMs, which are inspired by LVLM's different sensitivity to image corruption for member and non-member images. We first perform an MIA method under the white-box setting, where we can obtain the embeddings of the image through the vision part of the target LVLM. The attacks are based on the embedding similarity between the image and its corrupted version. We further explore a more practical scenario where we have no knowledge about target LVLMs and we can only query the target LVLMs with an image and a textual instruction. We then conduct the attack by utilizing the output text embeddings' similarity. Experiments on existing datasets validate the effectiveness of our proposed methods under those two different settings.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 45 of its 63 references that are in the map. First posted on arXiv 14 Jun 2025.

Builds on

45 of 63 references.

References · 45

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2024The Llama 3 Herd of Modelscited by 14,715
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2025Qwen3 Technical Reportcited by 8,820
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  8. 2025Qwen2.5-VL Technical Reportcited by 5,587
  9. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  10. 2023A Survey of Large Language Modelscited by 2,576
  11. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  12. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
33 more
  1. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  2. 2020Extracting Training Data from Large Language Modelscited by 2,189
  3. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  4. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  5. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  6. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  7. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,216
  8. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,050
  9. 2021Membership Inference Attacks From First Principlescited by 878
  10. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
  11. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 838
  12. 2023LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attentioncited by 781
  13. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 763
  14. 2024Yi: Open Foundation Models by 01.AIcited by 719
  15. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  16. 2020Label-Only Membership Inference Attackscited by 388
  17. 2023Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Modelscited by 357
  18. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 271
  19. 2023Membership Inference Attacks against Language Models via Neighbourhood Comparisoncited by 258
  20. 2023Proving Test Set Contamination in Black Box Language Modelscited by 230
  21. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 175
  22. 2024SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehensioncited by 146
  23. 2024A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthinesscited by 127
  24. 2024Benchmarking and Improving Detail Image Captioncited by 81
  25. 2021EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learningcited by 73
  26. 2024MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMscited by 72
  27. 2023Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Studycited by 38
  28. 2024Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysiscited by 23
  29. 2020Understanding Guided Image Captioning Performance across Domainscited by 21
  30. 2024Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotationcited by 21
  31. 2024LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learningcited by 17
  32. 2025LanP: Rethinking the Impact of Language Priors in Large Vision-Language Modelscited by 14
  33. 2024Divide-Verify-Refine: Can LLMs Self-Align with Complex Instructions?cited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthinesscited by 7
  2. 2026DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distractioncited by 0
  3. 2026Revealing Training Data Exposure in Vision Language Large Models via Parameter Gradientscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Models
  2. 2024Membership Inference Attacks against Large Vision-Language Models
  3. 2025Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
  4. 2026Single-Sample Black-Box Membership Inference Attack against Vision-Language Models via Cross-modal Semantic Alignment
  5. 2025Membership Inference Attacks Against Vision-Language Models
  6. 2024A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends
  7. 2026COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration
  8. 2025Revisiting Data Auditing in Large Vision-Language Models