---
title: "Image Corruption-Inspired Membership Inference Attacks against"
description: "The authors propose ICIMIA (Image Corruption-Inspired Membership Inference Attacks). 0.652 AUC. 64 references, cited by 1 paper here."
authors: ["Zongyu Wu", "Minhua Lin", "Zhiwei Zhang", "Fali Wang", "Xianren Zhang", "Xiang Zhang", "Suhang Wang"]
year: 2026
venue: "Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.eacl-long.371/"
doi: "10.18653/v1/2026.eacl-long.371"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wu-2026-image-corruption-inspired-membership-inference/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wu-2026-image-corruption-inspired-membership-inference/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/13/) / Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models

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

**Authors:** Zongyu Wu, [Minhua Lin](https://md.research.elamur.ai/free/en/authors/minhua-lin/), [Zhiwei Zhang](https://md.research.elamur.ai/free/en/authors/zhiwei-zhang/), [Fali Wang](https://md.research.elamur.ai/free/en/authors/fali-wang/), [Xianren Zhang](https://md.research.elamur.ai/free/en/authors/xianren-zhang/), [Xiang Zhang](https://md.research.elamur.ai/free/en/authors/xiang-zhang/) and [Suhang Wang](https://md.research.elamur.ai/free/en/authors/suhang-wang/) · **Year:** 2026 · **Venue:** [Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.eacl-long.371/) · [PDF](https://aclanthology.org/2026.eacl-long.371.pdf) · [DOI 10.18653/v1/2026.eacl-long.371](https://doi.org/10.18653/v1/2026.eacl-long.371) · [OpenAlex](https://openalex.org/W7140102958)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper asks whether someone holding only an image, with no caption, can tell if that image was in the training data of a large vision-language model (LVLM). This matters for privacy and copyright. The authors propose ICIMIA (Image Corruption-Inspired Membership Inference Attacks). The idea is that a model which has seen an image during training should react less to damaged versions of it. ICIMIA corrupts the target image with Gaussian Blur, Motion Blur or JPEG compression and scores how much the model's response changes.

There are two settings:
- **White-box:** the score is the similarity between the embeddings of the original and corrupted images, taken from the vision encoder plus alignment module.
- **Black-box:** the attacker can only send queries, so the score compares embeddings of the generated text.

On VL-MIA/Flickr with LLaVA-1.5 models, both variants work. The query-only attack even beats several baselines that need output logits.

## Key points
- Preliminary histograms on LLaVA-1.5-7B and VL-MIA/Flickr show that member images keep higher similarity under corruption than non-members. This holds both in embedding space and in output text.
- In the black-box setting on LLaVA-1.5-7B, the attack achieves 0.652 AUC, along with 0.137 TPR when the FPR is fixed at 5%.
- The choice of corruption matters:
  - Blur-based corruptions clearly beat JPEG compression in the embedding attack.
  - The embedding attack works best with small blur kernels (tested range 3–45).
  - The text-based attack prefers larger kernels (tested range 15–55).
- Using raw CLIP vision-encoder embeddings, without the alignment module, performs slightly better. Since CLIP is frozen in LLaVA-1.5, the images may also be in CLIP's original training data, so the authors call for new benchmarks.
- The method fails on VL-MIA/DALL-E. There, non-member images generated by DALL·E 2 are unusually robust to corruption.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Pennsylvania State University](https://md.research.elamur.ai/free/en/universities/pennsylvania-state-university/) — University, State College, United States · 56 works · 5,360 citations

📚 Shelves (3): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 657 works

## Cite

Cite as: Zongyu Wu, Minhua Lin, Zhiwei Zhang, Fali Wang, Xianren Zhang, Xiang Zhang and Suhang Wang. 2026. Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{wu2026image,
  title = {{Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models}},
  author = {Zongyu Wu, Minhua Lin, Zhiwei Zhang, Fali Wang, Xianren Zhang, Xiang Zhang and Suhang Wang},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.371},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.371}
}
```

- [← previous IITKanBDone at SemEval-2026 Task 8: ELSER-Based Sparse Retrieval with Mistral-7B for Multi-Turn RAG Evaluation](https://md.research.elamur.ai/free/en/papers/ray-2026-iitkanbdone-semeval-2026-task-8/)
- [next → Improving Dialect Robustness in Large Language Models via LoRA and Mixture-of-Experts](https://md.research.elamur.ai/free/en/papers/maheshwari-2026-improving-dialect-robustness-large-language/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/13/)

## References

64 references, 23 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. [Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-vl-versatile-vision-language/). arXiv preprint arXiv:2308.12966.
2. G. Bradski. 2000. The OpenCV Library. Dr. Dobb’s Journal of Software Tools. [find](https://scholar.google.com/scholar?q=G%2E+Bradski%2E+2000%2E+The+OpenCV+Library%2E+Dr%2E+Dobb%E2%80%99s+Journal+of+Software+Tools%2E)
3. Davide Bucciarelli, Nicholas Moratelli, Marcella Cornia, Lorenzo Baraldi, and Rita Cucchiara. 2024. Personalizing multimodal large language models for image captioning: an experimental analysis. arXiv preprint arXiv:2412.03665. — [arXiv:2412.03665](https://arxiv.org/abs/2412.03665) [find](https://scholar.google.com/scholar?q=Davide+Bucciarelli%2C+Nicholas+Moratelli%2C+Marcella+Cornia%2C+Lorenzo+Baraldi%2C+and+Rita+Cucchiara%2E+2024%2E+Personalizing+multimodal+large+language+models+for+image+captioning%3A+an+experimental+analysis%2E+arXiv)
4. Minwoo Byeon, Beomhee Park, Haecheon Kim, Sungjun Lee, Woonhyuk Baek, and Saehoon Kim. 2022. Coyo-700m: Image-text pair dataset. [https://github.com/kakaobrain/coyo-dataset](https://github.com/kakaobrain/coyo-dataset). [↗](https://github.com/kakaobrain/coyo-dataset)
5. Nicholas Carlini, Steve Chien, Milad Nasr, Shuang Song, Andreas Terzis, and Florian Tramer. 2022. Membership inference attacks from first principles. In 2022 IEEE symposium on security and privacy (SP), pages 1897–1914. [find](https://scholar.google.com/scholar?q=Nicholas+Carlini%2C+Steve+Chien%2C+Milad+Nasr%2C+Shuang+Song%2C+Andreas+Terzis%2C+and+Florian+Tramer%2E+2022%2E+Membership+inference+attacks+from+first+principles%2E+In+2022+IEEE+symposium+on+security+and+privacy+%28SP)
6. Nicholas Carlini, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tramer, and Chiyuan Zhang. 2023. Quantifying memorization across neural language models. In The Eleventh International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Nicholas+Carlini%2C+Daphne+Ippolito%2C+Matthew+Jagielski%2C+Katherine+Lee%2C+Florian+Tramer%2C+and+Chiyuan+Zhang%2E+2023%2E+Quantifying+memorization+across+neural+language+models%2E+In+The+Eleventh+International+Conf)
7. Nicholas Carlini, Chang Liu, Úlfar Erlingsson, Jernej Kos, and Dawn Song. 2019. [The secret sharer: Evaluating and testing unintended memorization in neural networks](https://md.research.elamur.ai/free/en/papers/carlini-2018-secret-sharer-evaluating-testing-unintended/). In Proceedings of the 28th USENIX Conference on Security Symposium, pages 267–284.
8. Nicholas Carlini, Florian Tramèr, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Úlfar Erlingsson, Alina Oprea, and Colin Raffel. 2021. [Extracting training data from large language models](https://md.research.elamur.ai/free/en/papers/carlini-2020-extracting-training-data-large-language/). In 30th USENIX Security Symposium (USENIX Security), p…
9. Soravit Changpinyo, Piyush Sharma, Nan Ding, and Radu Soricut. 2021. Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3558–3568. [find](https://scholar.google.com/scholar?q=Soravit+Changpinyo%2C+Piyush+Sharma%2C+Nan+Ding%2C+and+Radu+Soricut%2E+2021%2E+Conceptual+12m%3A+Pushing+web%2Dscale+image%2Dtext+pre%2Dtraining+to+recognize+long%2Dtail+visual+concepts%2E+In+Proceedings+of+the+IEEE%2FCVF+Co)
10. Jun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechun Liu, Pengchuan Zhang, Raghuraman Krishnamoorthi, Vikas Chandra, Yunyang Xiong, and Mohamed Elhoseiny. 2023. [Minigpt-v2: large language model as a unified interface for vision-language multi-task learning](https://md.research.elamur.ai/free/en/papers/chen-2023-minigpt-v2-large-language-model/). arXiv preprint arXiv:2310.09478.
11. Zhe Chen, Weiyun Wang, Hao Tian, Shenglong Ye, Zhangwei Gao, Erfei Cui, Wenwen Tong, Kongzhi Hu, Jiapeng Luo, Zheng Ma, Ji Ma, Jiaqi Wang, Xiaoyi Dong, Hang Yan, Hewei Guo, Conghui He, Botian Shi, Zhenjiang Jin, Chao Xu, Bin Wang, Xingjian Wei, Wei Li, Wenjian Zhang, Bo Zhang, Pinlong Cai, Licheng W… — [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://md.research.elamur.ai/free/en/papers/chen-2024-far-gpt-4v-closing/)
12. Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, and Jifeng Dai. 2024b. [Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks](https://md.research.elamur.ai/free/en/papers/chen-2023-internvl-scaling-up-vision/). In Proceedings of the IEEE/C…
13. Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. [find](https://scholar.google.com/scholar?q=Wei%2DLin+Chiang%2C+Zhuohan+Li%2C+Zi+Lin%2C+Ying+Sheng%2C+Zhanghao+Wu%2C+Hao+Zhang%2C+Lianmin+Zheng%2C+Siyuan+Zhuang%2C+Yonghao+Zhuang%2C+Joseph+E%2E+Gonzalez%2C+Ion+Stoica%2C+and+Eric+P%2E+Xing%2E+2023%2E+Vicuna%3A+An+open%2Dsource+cha)
14. Christopher A. Choquette-Choo, Florian Tramer, Nicholas Carlini, and Nicolas Papernot. 2021. Label-only membership inference attacks. In Proceedings of the 38th International Conference on Machine Learning, pages 1964–1974. [find](https://scholar.google.com/scholar?q=Christopher+A%2E+Choquette%2DChoo%2C+Florian+Tramer%2C+Nicholas+Carlini%2C+and+Nicolas+Papernot%2E+2021%2E+Label%2Donly+membership+inference+attacks%2E+In+Proceedings+of+the+38th+International+Conference+on+Machine+Lea)
15. Hongyuan Dong, Jiawen Li, Bohong Wu, Jiacong Wang, Yuan Zhang, and Haoyuan Guo. 2024. Benchmarking and improving detail image caption. arXiv preprint arXiv:2405.19092. — [arXiv:2405.19092](https://arxiv.org/abs/2405.19092) [find](https://scholar.google.com/scholar?q=Hongyuan+Dong%2C+Jiawen+Li%2C+Bohong+Wu%2C+Jiacong+Wang%2C+Yuan+Zhang%2C+and+Haoyuan+Guo%2E+2024%2E+Benchmarking+and+improving+detail+image+caption%2E+arXiv+preprint+arXiv%3A2405%2E19092%2E+%E2%80%94+%5BarXiv%3A2405%2E19092%5D%28https%3A%2F%2Farx)
16. Michael Duan, Anshuman Suri, Niloofar Mireshghallah, Sewon Min, Weijia Shi, Luke Zettlemoyer, Yulia Tsvetkov, Yejin Choi, David Evans, and Hannaneh Hajishirzi. 2024. [Do membership inference attacks work on large language models?](https://md.research.elamur.ai/free/en/papers/duan-2024-membership-inference-attacks-work-large/) In Conference on Language Modeling.
17. Chaoyou Fu, Yi-Fan Zhang, Shukang Yin, Bo Li, Xinyu Fang, Sirui Zhao, Haodong Duan, Xing Sun, Ziwei Liu, Liang Wang, Caifeng Shan, and Ran He. 2024. Mme-survey: A comprehensive survey on evaluation of multimodal llms. arXiv preprint arXiv:2411.15296. — [arXiv:2411.15296](https://arxiv.org/abs/2411.15296) [find](https://scholar.google.com/scholar?q=Chaoyou+Fu%2C+Yi%2DFan+Zhang%2C+Shukang+Yin%2C+Bo+Li%2C+Xinyu+Fang%2C+Sirui+Zhao%2C+Haodong+Duan%2C+Xing+Sun%2C+Ziwei+Liu%2C+Liang+Wang%2C+Caifeng+Shan%2C+and+Ran+He%2E+2024%2E+Mme%2Dsurvey%3A+A+comprehensive+survey+on+evaluation+of)
18. Hongsheng Hu, Zoran Salcic, Lichao Sun, Gillian Dobbie, Philip S. Yu, and Xuyun Zhang. 2022a. Membership inference attacks on machine learning: A survey. ACM Computing Surveys, 54. [find](https://scholar.google.com/scholar?q=Hongsheng+Hu%2C+Zoran+Salcic%2C+Lichao+Sun%2C+Gillian+Dobbie%2C+Philip+S%2E+Yu%2C+and+Xuyun+Zhang%2E+2022a%2E+Membership+inference+attacks+on+machine+learning%3A+A+survey%2E+ACM+Computing+Surveys%2C+54%2E)
19. Pingyi Hu, Zihan Wang, Ruoxi Sun, Hu Wang, and Minhui Xue. 2022b. M 4 i: Multi-modal models membership inference. In Advances in Neural Information Processing Systems, volume 35, pages 1867–1882. [find](https://scholar.google.com/scholar?q=Pingyi+Hu%2C+Zihan+Wang%2C+Ruoxi+Sun%2C+Hu+Wang%2C+and+Minhui+Xue%2E+2022b%2E+M+4+i%3A+Multi%2Dmodal+models+membership+inference%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+35%2C+pages+1867%E2%80%931882%2E)
20. Yuke Hu, Zheng Li, Zhihao Liu, Yang Zhang, Zhan Qin, Kui Ren, and Chun Chen. 2025. Membership inference attacks against vision-language models. arXiv preprint arXiv:2501.18624. — [arXiv:2501.18624](https://arxiv.org/abs/2501.18624) [find](https://scholar.google.com/scholar?q=Yuke+Hu%2C+Zheng+Li%2C+Zhihao+Liu%2C+Yang+Zhang%2C+Zhan+Qin%2C+Kui+Ren%2C+and+Chun+Chen%2E+2025%2E+Membership+inference+attacks+against+vision%2Dlanguage+models%2E+arXiv+preprint+arXiv%3A2501%2E18624%2E+%E2%80%94+%5BarXiv%3A2501%2E18624%5D%28ht)
21. Myeongseob Ko, Ming Jin, Chenguang Wang, and Ruoxi Jia. 2023. Practical membership inference attacks against large-scale multi-modal models: A pilot study. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 4871–4881. [find](https://scholar.google.com/scholar?q=Myeongseob+Ko%2C+Ming+Jin%2C+Chenguang+Wang%2C+and+Ruoxi+Jia%2E+2023%2E+Practical+membership+inference+attacks+against+large%2Dscale+multi%2Dmodal+models%3A+A+pilot+study%2E+In+Proceedings+of+the+IEEE%2FCVF+International)
22. Klas Leino and Matt Fredrikson. 2020. Stolen memories: Leveraging model memorization for calibrated white-box membership inference. In 29th USENIX security symposium (USENIX Security), pages 1605– 1622. [find](https://scholar.google.com/scholar?q=Klas+Leino+and+Matt+Fredrikson%2E+2020%2E+Stolen+memories%3A+Leveraging+model+memorization+for+calibrated+white%2Dbox+membership+inference%2E+In+29th+USENIX+security+symposium+%28USENIX+Security%29%2C+pages+1605%E2%80%93+162)
23. Bohao Li, Yuying Ge, Yi Chen, Yixiao Ge, Ruimao Zhang, and Ying Shan. 2024a. Seed-bench-2-plus: Benchmarking multimodal large language models with text-rich visual comprehension. arXiv preprint arXiv:2404.16790. — [arXiv:2404.16790](https://arxiv.org/abs/2404.16790) [find](https://scholar.google.com/scholar?q=Bohao+Li%2C+Yuying+Ge%2C+Yi+Chen%2C+Yixiao+Ge%2C+Ruimao+Zhang%2C+and+Ying+Shan%2E+2024a%2E+Seed%2Dbench%2D2%2Dplus%3A+Benchmarking+multimodal+large+language+models+with+text%2Drich+visual+comprehension%2E+arXiv+preprint+arXiv%3A)
24. Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, and Jianfeng Gao. 2023a. [Llava-med: Training a large language-and-vision assistant for biomedicine in one day](https://md.research.elamur.ai/free/en/papers/li-2023-llava-med-training-large-language/). In Advances in Neural Information Processing Systems, pages 28541–28564.
25. Jiacheng Li, Ninghui Li, and Bruno Ribeiro. 2021. Membership inference attacks and defenses in classification models. In Proceedings of the Eleventh ACM Conference on Data and Application Security and Privacy, pages 5–16. [find](https://scholar.google.com/scholar?q=Jiacheng+Li%2C+Ninghui+Li%2C+and+Bruno+Ribeiro%2E+2021%2E+Membership+inference+attacks+and+defenses+in+classification+models%2E+In+Proceedings+of+the+Eleventh+ACM+Conference+on+Data+and+Application+Security+and)
26. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023b. [BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models](https://md.research.elamur.ai/free/en/papers/li-2023-blip-2-bootstrapping-language-image/). In Proceedings of the 40th International Conference on Machine Learning, pages 19730–19742.
27. Zhan Li, Yongtao Wu, Yihang Chen, Francesco Tonin, Elias Abad Rocamora, and Volkan Cevher. 2024b. Membership inference attacks against large vision-language models. In Advances in Neural Information Processing Systems, pages 98645–98674. [find](https://scholar.google.com/scholar?q=Zhan+Li%2C+Yongtao+Wu%2C+Yihang+Chen%2C+Francesco+Tonin%2C+Elias+Abad+Rocamora%2C+and+Volkan+Cevher%2E+2024b%2E+Membership+inference+attacks+against+large+vision%2Dlanguage+models%2E+In+Advances+in+Neural+Information+P)
28. Zhang Li, Biao Yang, Qiang Liu, Zhiyin Ma, Shuo Zhang, Jingxu Yang, Yabo Sun, Yuliang Liu, and Xiang Bai. 2024c. Monkey: Image resolution and text label are important things for large multi-modal models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pag… [find](https://scholar.google.com/scholar?q=Zhang+Li%2C+Biao+Yang%2C+Qiang+Liu%2C+Zhiyin+Ma%2C+Shuo+Zhang%2C+Jingxu+Yang%2C+Yabo+Sun%2C+Yuliang+Liu%2C+and+Xiang+Bai%2E+2024c%2E+Monkey%3A+Image+resolution+and+text+label+are+important+things+for+large+multi%2Dmodal+mode)
29. Minhua Lin, Zhengzhang Chen, Yanchi Liu, Xujiang Zhao, Zongyu Wu, Junxiang Wang, Xiang Zhang, Suhang Wang, and Haifeng Chen. 2024. Decoding time series with llms: A multi-agent framework for cross-domain annotation. arXiv preprint arXiv:2410.17462. [find](https://scholar.google.com/scholar?q=Minhua+Lin%2C+Zhengzhang+Chen%2C+Yanchi+Liu%2C+Xujiang+Zhao%2C+Zongyu+Wu%2C+Junxiang+Wang%2C+Xiang+Zhang%2C+Suhang+Wang%2C+and+Haifeng+Chen%2E+2024%2E+Decoding+time+series+with+llms%3A+A+multi%2Dagent+framework+for+cross%2Ddom)
30. Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick. 2014. [Microsoft coco: Common objects in context](https://md.research.elamur.ai/free/en/papers/lin-2014-microsoft-coco-common-objects-context/). In Computer Vision – ECCV 2014, pages 740–755.
31. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2024a. [Improved baselines with visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-improved-baselines-visual-instruction-tuning/). In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 26296–26306.
32. Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024b. Llava-next: Improved reasoning, ocr, and world knowledge. [find](https://scholar.google.com/scholar?q=Haotian+Liu%2C+Chunyuan+Li%2C+Yuheng+Li%2C+Bo+Li%2C+Yuanhan+Zhang%2C+Sheng+Shen%2C+and+Yong+Jae+Lee%2E+2024b%2E+Llava%2Dnext%3A+Improved+reasoning%2C+ocr%2C+and+world+knowledge%2E)
33. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. [Visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-visual-instruction-tuning/). In Advances in Neural Information Processing Systems, volume 36, pages 34892–34916.
34. Hongbin Liu, Jinyuan Jia, Wenjie Qu, and Neil Zhenqiang Gong. 2021. Encodermi: Membership inference against pre-trained encoders in contrastive learning. In Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, pages 2081–2095. [find](https://scholar.google.com/scholar?q=Hongbin+Liu%2C+Jinyuan+Jia%2C+Wenjie+Qu%2C+and+Neil+Zhenqiang+Gong%2E+2021%2E+Encodermi%3A+Membership+inference+against+pre%2Dtrained+encoders+in+contrastive+learning%2E+In+Proceedings+of+the+2021+ACM+SIGSAC+Conferen)
35. Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Schölkopf, Mrinmaya Sachan, and Taylor Berg-Kirkpatrick. 2023. [Membership inference attacks against language models via neighbourhood comparison](https://md.research.elamur.ai/free/en/papers/mattern-2023-membership-inference-attacks-against-language/). In Findings of the Association for Computational Linguistics: ACL 2023, pages 11330– 113…
36. Fatemehsadat Mireshghallah, Archit Uniyal, Tianhao Wang, David K Evans, and Taylor Berg-Kirkpatrick. 2022. An empirical analysis of memorization in fine-tuned autoregressive language models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1816–1826. [find](https://scholar.google.com/scholar?q=Fatemehsadat+Mireshghallah%2C+Archit+Uniyal%2C+Tianhao+Wang%2C+David+K+Evans%2C+and+Taylor+Berg%2DKirkpatrick%2E+2022%2E+An+empirical+analysis+of+memorization+in+fine%2Dtuned+autoregressive+language+models%2E+In+Procee)
37. Milad Nasr, Reza Shokri, and Amir Houmansadr. 2019. Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning. In 2019 IEEE symposium on security and privacy (SP), pages 739–753. [find](https://scholar.google.com/scholar?q=Milad+Nasr%2C+Reza+Shokri%2C+and+Amir+Houmansadr%2E+2019%2E+Comprehensive+privacy+analysis+of+deep+learning%3A+Passive+and+active+white%2Dbox+inference+attacks+against+centralized+and+federated+learning%2E+In+2019+)
38. Yonatan Oren, Nicole Meister, Niladri S. Chatterji, Faisal Ladhak, and Tatsunori Hashimoto. 2024. Proving test set contamination in black-box language models. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yonatan+Oren%2C+Nicole+Meister%2C+Niladri+S%2E+Chatterji%2C+Faisal+Ladhak%2C+and+Tatsunori+Hashimoto%2E+2024%2E+Proving+test+set+contamination+in+black%2Dbox+language+models%2E+In+The+Twelfth+International+Conference+o)
39. Guilherme Penedo, Quentin Malartic, Daniel Hesslow, Ruxandra Cojocaru, Alessandro Cappelli, Hamza Alobeidli, Baptiste Pannier, Ebtesam Almazrouei, and Julien Launay. 2023. The refinedweb dataset for falcon llm: Outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306… [find](https://scholar.google.com/scholar?q=Guilherme+Penedo%2C+Quentin+Malartic%2C+Daniel+Hesslow%2C+Ruxandra+Cojocaru%2C+Alessandro+Cappelli%2C+Hamza+Alobeidli%2C+Baptiste+Pannier%2C+Ebtesam+Almazrouei%2C+and+Julien+Launay%2E+2023%2E+The+refinedweb+dataset+for+f)
40. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In Proceedings of the 38th Internatio…
41. Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. [Hierarchical text-conditional image generation with clip latents](https://md.research.elamur.ai/free/en/papers/ramesh-2022-hierarchical-text-conditional-image-generation/). arXiv preprint arXiv:2204.06125.
42. Jie Ren, Kangrui Chen, Chen Chen, Vikash Sehwag, Yue Xing, Jiliang Tang, and Lingjuan Lyu. 2025. Self-comparison for dataset-level membership inference in large (vision-)language model. In Proceedings of the ACM on Web Conference 2025, page 910–920. [find](https://scholar.google.com/scholar?q=Jie+Ren%2C+Kangrui+Chen%2C+Chen+Chen%2C+Vikash+Sehwag%2C+Yue+Xing%2C+Jiliang+Tang%2C+and+Lingjuan+Lyu%2E+2025%2E+Self%2Dcomparison+for+dataset%2Dlevel+membership+inference+in+large+%28vision%2D%29language+model%2E+In+Proceedings)
43. Alfréd Rényi. 1961. On measures of entropy and information. In Proceedings of the fourth Berkeley symposium on mathematical statistics and probability, volume 1: contributions to the theory of statistics. University of California Press. [find](https://scholar.google.com/scholar?q=Alfr%C3%A9d+R%C3%A9nyi%2E+1961%2E+On+measures+of+entropy+and+information%2E+In+Proceedings+of+the+fourth+Berkeley+symposium+on+mathematical+statistics+and+probability%2C+volume+1%3A+contributions+to+the+theory+of+statist)
44. Shahbaz Rezaei and Xin Liu. 2021. On the difficulty of membership inference attacks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 7892–7900. [find](https://scholar.google.com/scholar?q=Shahbaz+Rezaei+and+Xin+Liu%2E+2021%2E+On+the+difficulty+of+membership+inference+attacks%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29%2C+pages+7892%E2%80%937900%2E)
45. Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid, Yann Ollivier, and Hervé Jégou. 2019. White-box vs black-box: Bayes optimal strategies for membership inference. In Proceedings of the 36th International Conference on Machine Learning, pages 5558–5567. [find](https://scholar.google.com/scholar?q=Alexandre+Sablayrolles%2C+Matthijs+Douze%2C+Cordelia+Schmid%2C+Yann+Ollivier%2C+and+Herv%C3%A9+J%C3%A9gou%2E+2019%2E+White%2Dbox+vs+black%2Dbox%3A+Bayes+optimal+strategies+for+membership+inference%2E+In+Proceedings+of+the+36th+Int)
46. Ahmed Salem, Yang Zhang, Mathias Humbert, Pascal Berrang, Mario Fritz, and Michael Backes. 2018. Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models. arXiv preprint arXiv:1806.01246. — [arXiv:1806.01246](https://arxiv.org/abs/1806.01246) [find](https://scholar.google.com/scholar?q=Ahmed+Salem%2C+Yang+Zhang%2C+Mathias+Humbert%2C+Pascal+Berrang%2C+Mario+Fritz%2C+and+Michael+Backes%2E+2018%2E+Ml%2Dleaks%3A+Model+and+data+independent+membership+inference+attacks+and+defenses+on+machine+learning+mode)
47. Weijia Shi, Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu, Terra Blevins, Danqi Chen, and Luke Zettlemoyer. 2024. Detecting pretraining data from large language models. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Weijia+Shi%2C+Anirudh+Ajith%2C+Mengzhou+Xia%2C+Yangsibo+Huang%2C+Daogao+Liu%2C+Terra+Blevins%2C+Danqi+Chen%2C+and+Luke+Zettlemoyer%2E+2024%2E+Detecting+pretraining+data+from+large+language+models%2E+In+The+Twelfth+Intern)
48. Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov. 2017. [Membership inference attacks against machine learning models](https://md.research.elamur.ai/free/en/papers/shokri-2016-membership-inference-attacks-against-machine/). In 2017 IEEE symposium on security and privacy (SP), pages 3–18.
49. Congzheng Song, Thomas Ristenpart, and Vitaly Shmatikov. 2017. Machine learning models that remember too much. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, pages 587–601. [find](https://scholar.google.com/scholar?q=Congzheng+Song%2C+Thomas+Ristenpart%2C+and+Vitaly+Shmatikov%2E+2017%2E+Machine+learning+models+that+remember+too+much%2E+In+Proceedings+of+the+2017+ACM+SIGSAC+Conference+on+Computer+and+Communications+Security%2C)
50. InternLM Team. 2023. Internlm: A multilingual language model with progressively enhanced capabilities. [https://github.com/InternLM/](https://github.com/InternLM/) InternLM-techreport. [↗](https://github.com/InternLM/)
51. Shengbang Tong, Ellis Brown, Penghao Wu, Sanghyun Woo, Manoj Middepogu, Sai Charitha Akula, Jihan Yang, Shusheng Yang, Adithya Iyer, Xichen Pan, Austin Wang, Rob Fergus, Yann LeCun, and Saining Xie. 2024. [Cambrian-1: A fully open, vision-centric exploration of multimodal llms](https://md.research.elamur.ai/free/en/papers/tong-2024-cambrian-1-fully-open-vision/). arXiv preprint arXiv:2…
52. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023a. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv p…
53. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,… — [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/)
54. Fali Wang, Zhiwei Zhang, Xianren Zhang, Zongyu Wu, TzuHao Mo, Qiuhao Lu, Wanjing Wang, Rui Li, Junjie Xu, Xianfeng Tang, Qi He, Yao Ma, Ming Huang, and Suhang Wang. 2025. A comprehensive survey of small language models in the era of large language models: Techniques, enhancements, applications, coll… [find](https://scholar.google.com/scholar?q=Fali+Wang%2C+Zhiwei+Zhang%2C+Xianren+Zhang%2C+Zongyu+Wu%2C+TzuHao+Mo%2C+Qiuhao+Lu%2C+Wanjing+Wang%2C+Rui+Li%2C+Junjie+Xu%2C+Xianfeng+Tang%2C+Qi+He%2C+Yao+Ma%2C+Ming+Huang%2C+and+Suhang+Wang%2E+2025%2E+A+comprehensive+survey+of+sma)
55. Zongyu Wu, Yuwei Niu, Hongcheng Gao, Minhua Lin, Zhiwei Zhang, Zhifang Zhang, Qi Shi, Yilong Wang, Sike Fu, Junjie Xu, Junjie Ao, Enyan Dai, Lei Feng, Xiang Zhang, and Suhang Wang. 2025. Lanp: Rethinking the impact of language priors in large vision-language models. arXiv preprint arXiv:2502.12359. — [arXiv:2502.12359](https://arxiv.org/abs/2502.12359) [find](https://scholar.google.com/scholar?q=Zongyu+Wu%2C+Yuwei+Niu%2C+Hongcheng+Gao%2C+Minhua+Lin%2C+Zhiwei+Zhang%2C+Zhifang+Zhang%2C+Qi+Shi%2C+Yilong+Wang%2C+Sike+Fu%2C+Junjie+Xu%2C+Junjie+Ao%2C+Enyan+Dai%2C+Lei+Feng%2C+Xiang+Zhang%2C+and+Suhang+Wang%2E+2025%2E+Lanp%3A+Rethink)
56. Junjie Xu, Zongyu Wu, Minhua Lin, Xiang Zhang, and Suhang Wang. 2024. Llm and gnn are complementary: Distilling llm for multimodal graph learning. arXiv preprint arXiv:2406.01032. — [arXiv:2406.01032](https://arxiv.org/abs/2406.01032) [find](https://scholar.google.com/scholar?q=Junjie+Xu%2C+Zongyu+Wu%2C+Minhua+Lin%2C+Xiang+Zhang%2C+and+Suhang+Wang%2E+2024%2E+Llm+and+gnn+are+complementary%3A+Distilling+llm+for+multimodal+graph+learning%2E+arXiv+preprint+arXiv%3A2406%2E01032%2E+%E2%80%94+%5BarXiv%3A2406%2E01032%5D)
57. Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, Cong Wei, Botao Yu, Ruibin Yuan, Renliang Sun, Ming Yin, Boyuan Zheng, Zhenzhu Yang, Yibo Liu, Wenhao Huang, Huan Sun, Yu Su, and Wenhu Chen. 2024. [Mmmu: A massive multi-disc…](https://md.research.elamur.ai/free/en/papers/yue-2023-mmmu-massive-multi-discipline-multimodal/)
58. Jingyang Zhang, Jingwei Sun, Eric Yeats, Yang Ouyang, Martin Kuo, Jianyi Zhang, Hao Frank Yang, and Hai Li. 2025a. Min-k%++: Improved baseline for pre-training data detection from large language models. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Jingyang+Zhang%2C+Jingwei+Sun%2C+Eric+Yeats%2C+Yang+Ouyang%2C+Martin+Kuo%2C+Jianyi+Zhang%2C+Hao+Frank+Yang%2C+and+Hai+Li%2E+2025a%2E+Min%2Dk%25%2B%2B%3A+Improved+baseline+for+pre%2Dtraining+data+detection+from+large+language+model)
59. Renrui Zhang, Jiaming Han, Chris Liu, Peng Gao, Aojun Zhou, Xiangfei Hu, Shilin Yan, Pan Lu, Hongsheng Li, and Yu Qiao. 2023. [Llama-adapter: Efficient fine-tuning of language models with zero-init attention](https://md.research.elamur.ai/free/en/papers/zhang-2023-llama-adapter-efficient-fine-tuning/). arXiv preprint arXiv:2303.16199.
60. Xianren Zhang, Xianfeng Tang, Hui Liu, Zongyu Wu, Qi He, Dongwon Lee, and Suhang Wang. 2025b. Divide-verify-refine: Can LLMs self-align with complex instructions? In Findings of the Association for Computational Linguistics: ACL 2025, pages 13783– 13800. [find](https://scholar.google.com/scholar?q=Xianren+Zhang%2C+Xianfeng+Tang%2C+Hui+Liu%2C+Zongyu+Wu%2C+Qi+He%2C+Dongwon+Lee%2C+and+Suhang+Wang%2E+2025b%2E+Divide%2Dverify%2Drefine%3A+Can+LLMs+self%2Dalign+with+complex+instructions%3F+In+Findings+of+the+Association+for+Co)
61. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie, and Ji-Rong Wen. 2023. [A survey of l…](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/)
62. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2024. [MiniGPT-4: Enhancing vision-language understanding with advanced large language models](https://md.research.elamur.ai/free/en/papers/zhu-2023-minigpt-4-enhancing-vision-language/). In The Twelfth International Conference on Learning Representations.
63. Name VL-MIA/Flickr VL-MIA/Flickr 2K MS COCO Flickr 300 300 MS COCO Flickr 1000 1000 Source of Member Data Source of Non-member Data \#Member Data \#Non-member Data *Table 4: Dataset statistics. The datasets are constructed by Li et al. (2024b).* AUC Method TPR at 5% FPR LLaVA-1.5-7B LLaVA-1.5-13B LLaV… [find](https://scholar.google.com/scholar?q=Name+VL%2DMIA%2FFlickr+VL%2DMIA%2FFlickr+2K+MS+COCO+Flickr+300+300+MS+COCO+Flickr+1000+1000+Source+of+Member+Data+Source+of+Non%2Dmember+Data+%5C%23Member+Data+%5C%23Non%2Dmember+Data+%2ATable+4%3A+Dataset+statistics%2E+The+da)
64. Ours (Image_Sim, Gaussian Blur, Kernel Size 5) Ours (Image_Sim, Motion Blur, Kernel Size 5) Ours (Image_Sim, JPEG Compression, Quality = 5) *Table 5: Image MIA performance of our proposed approach on VL-MIA/Flickr 2K.* [find](https://scholar.google.com/scholar?q=Ours+%28Image%5FSim%2C+Gaussian+Blur%2C+Kernel+Size+5%29+Ours+%28Image%5FSim%2C+Motion+Blur%2C+Kernel+Size+5%29+Ours+%28Image%5FSim%2C+JPEG+Compression%2C+Quality+%3D+5%29+%2ATable+5%3A+Image+MIA+performance+of+our+proposed+approach+on+)

*Updated 1 November 2026*