CoChat
Sign Up
Cited by 15

The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.

Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation

Li, Yuying, Liu, Gaoyang, Wang, Chen, Yang, Yang·2025·ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
DOI 10.1109/icassp49660.2025.10889013
Open this paper in CoChat — free account

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icassp49660.2025.10889013

Cites

16 of 16 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Framework of S 2 MIA. Given a target sample, we divide it into the query text and the remaining text. We input the query text into a given RAG system, which retrieves the multiple samples most similar to the query test from the external database. These retrieved texts serve as the context for the LLM to generate responses. Consequently, if the target sample is present in the RAG's external database, the generated text should exhibit high semantic similarity and low perplexity to the remaining text.
Figure 1 Framework of S 2 MIA. Given a target sample, we divide it into the query text and the remaining text. We input the query text into a given RAG system, which retrieves the multiple samples most similar to the query test from the external database. These retrieved texts serve as the context for the LLM to generate responses. Consequently, if the target sample is present in the RAG's external database, the generated text should exhibit high semantic similarity and low perplexity to the remaining text.CC-BY · From the PDF
Figure 2 Illustration of the distribution of member versus non-member samples
Figure 2 Illustration of the distribution of member versus non-member samplesCC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 16 references

Research works printed but not linked: 26

  1. 10.1609/aaai.v38i17.29859 · DOI
  2. 10.1109/CVPR52733.2024.01845 · DOI
  3. Asai, Self-rag: Learning to retrieve, generate, and critique through self-reflection
  4. 10.18653/v1/2023.findings-emnlp.164 · DOI
  5. 10.1109/ICASSP48485.2024.10447448 · DOI
  6. 10.14722/aiscc.2024.23018 · DOI
  7. 10.1145/3637528.3671932 · DOI
  8. Anderson, 2024, Is my data in your retrieval database? membership inference attacks against retrieval augmented generation, CoRR
  9. 10.1109/ICCV51070.2023.00449 · DOI
  10. Meeus, Did the neurons read your book? document-level membership inference for large language models, 2369
  11. Maini, 2024, Llm dataset inference: Did you train on my dataset?, CoRR
  12. Zhou, 2024, Balancing diversity and risk in llm sampling: How to select your method and parameter for open-ended text generation, CoRR
  13. 10.18653/v1/2023.emnlp-main.765 · DOI
  14. Lin, Ra-dit: Retrieval-augmented dual instruction tuning
  15. 10.1145/3637528.3671470 · DOI · Paper page
  16. Panda, Privacy auditing of large language models
  17. Zeng, 2024, Mitigating the privacy issues in retrieval-augmented generation (rag) via pure synthetic data, CoRR
  18. 10.18653/v1/2024.emnlp-main.1236 · DOI
  19. Guu, Retrieval augmented language model pre-training, 3929
  20. Touvron, 2023, Llama 2: Open foundation and fine-tuned chat models, CoRR
  21. Duan, 2024, Do membership inference attacks work on large language models?, CoRR
  22. Duan, Are diffusion models vulnerable to membership inference attacks?, 8717
  23. 10.18653/v1/2023.findings-acl.719 · DOI
  24. Jain, 2023, Baseline defenses for adversarial attacks against aligned language models, CoRR
  25. 10.1145/3626772.3657959 · DOI
  26. Agarwal, 2024, Investigating the prompt leakage effect and black-box defenses for multi-turn llm interactions, CoRR

Cited by

See all 15

Metadata

Authors
Li, Y., Liu, G., Wang, C., & Yang, Y.
Affiliations
  • Hubei University,Key Laboratory of Intelligent Sensing System and Security (Ministry of Education), School of Artificial Intelligence,Wuhan,China
  • Huazhong University of Science and Technology,Hubei Key Laboratory of Smart Internet Technology,Wuhan,China
Venue
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher
IEEE
Published
2025-04-06
Pages
1-5
DOI
10.1109/icassp49660.2025.10889013
Cited by
15
References
16
Licence
Funders
  • National Natural Science Foundation of China
  • Ministry of Education

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation. https://app.cochat.ai/papers/10.1109/icassp49660.2025.10889013
The paper
Li, Y., Liu, G., Wang, C., & Yang, Y. (2025). Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation. ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp49660.2025.10889013