Membership Leakage in Label-Only Exposures
The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
Machine learning (ML) has been widely adopted in various privacy-critical applications, e.g., face recognition and medical image analysis. However, recent research has shown that ML models are vulnerable to attacks against their training data. Membership inference is one major attack in this domain: Given a data sample and model, an adversary aims to determine whether the sample is part of the model's training set. Existing membership inference attacks leverage the confidence scores returned by the model as their inputs (score-based attacks). However, these attacks can be easily mitigated if the model only exposes the predicted label, i.e., the final model decision. In this paper, we propose decision-based membership inference attacks and demonstrate that label-only exposures are also vulnerable to membership leakage. In particular, we develop two types of decision-based attacks, namely transfer attack and boundary attack. Empirical evaluation shows that our decision-based attacks can achieve remarkable performance, and even outperform the previous score-based attacks in some cases. We further present new insights on the success of membership inference based on quantitative and qualitative analysis, i.e., member samples of a model are more distant to the model's decision boundary than non-member samples. Finally, we evaluate multiple defense mechanisms against our decision-based attacks and show that our two types of attacks can bypass most of these defenses.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859
Calibrating Noise to Sensitivity in Private Data Analysis
Dwork, C., McSherry, F., Nissim, K., & Smith, A. (2006) · Lecture Notes in Computer Science · doi:10.1007/11681878_14 · Cited by 7,272
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754 · cited 10×
“In contrast to the prior score-based attacks[25, 31, 35, 46, 48, 49, 57] that directly exploit confidence scores as analysis objects, we place our focus on the antithesis of this observation, i.”
BackgroundMethodResultInfluentialThe Limitations of Deep Learning in Adversarial Settings
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z. B., & Swami, A. (2016) · 2016 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2016.36 · Cited by 3,993
Practical Black-Box Attacks against Machine Learning
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z. B., & Swami, A. (2017) · Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security · doi:10.1145/3052973.3053009 · Cited by 3,495
Machine Learning Applications in Cancer Prognosis and Prediction
Kourou, K., Exarchos, T. P., Exarchos, K. P., Karamouzis, M. V., & Fotiadis, D. I. (2015) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2014.11.005 · Cited by 3,338
Ensemble Adversarial Training: Attacks and Defenses
Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., & McDaniel, P. (2017) · arXiv · doi:10.48550/arxiv.1705.07204 · Cited by 2,176 · cited 1×
“, predicted label, is similar to that of adversarial attack [8, 10, 41, 42, 47, 52], For simplicity, we utilize adversarial example techniques to perturb the input to mislead the target model.”
MethodTransferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
Papernot, N., McDaniel, P., & Goodfellow, I. (2016) · arXiv · doi:10.48550/arxiv.1605.07277 · Cited by 1,326
Delving into Transferable Adversarial Examples and Black-box Attacks
Liu, Y., Chen, X., Liu, C., & Song, D. (2016) · arXiv · doi:10.48550/arxiv.1611.02770 · Cited by 1,310
Trojaning Attack on Neural Networks
Liu, Y., Ma, S., Aafer, Y., Lee, W.-C., Zhai, J., Wang, W., & Zhang, X. (2018) · Proceedings 2018 Network and Distributed System Security Symposium · doi:10.14722/ndss.2018.23291 · Cited by 1,270
Cited by
Membership Inference Attacks on Machine Learning: A Survey
Hu, H., Salcic, Z., Sun, L., Dobbie, G., Yu, P. S., & Zhang, X. (2022) · ACM Computing Surveys · doi:10.1145/3523273 · Cited by 564
Membership Inference Attacks From First Principles
Carlini, N., Chien, S., Nasr, M., Song, S., Terzis, A., & Tramèr, F. (2022) · 2022 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp46214.2022.9833649 · Cited by 502
A Survey of Privacy Attacks in Machine Learning
Rigaki, M., & Garcia, S. (2024) · ACM Computing Surveys · doi:10.1145/3624010 · Cited by 285
“A common design pattern for a lot of supervised learning attacks is the use of shadow models and meta-models or attack-models [3, 18, 29, 40, 46, 51, 68, 97, 106, 108, 110, 116, 125].”
BackgroundMembership Inference Attacks Against Sequential Recommender Systems
Zhu, Z., Wu, C., Fan, R., Lian, D., & Chen, E. (2023) · Proceedings of the ACM Web Conference 2023 · doi:10.1145/3543507.3583447 · Cited by 24
“In recent years, a more restricted scenario of MIAs, which is called label-only MIA [6, 21, 55], has been proposed.”
BackgroundAdvancing membership inference attacks: the present and the future
Li, Z., & Zhang, Y. (2025) · Security and Safety · doi:10.1051/sands/2024017 · Cited by 4
Self-citationMembership Inference Attacks against Language Models via Neighbourhood Comparison
Mattern, J., Mireshghallah, F., Jin, Z., Schölkopf, B., Sachan, M., & Berg-Kirkpatrick, T. (2023) · arXiv · doi:10.48550/arxiv.2305.18462 · Cited by 4
Metadata
- Authors
- Li, Z., & Zhang, Y.
- Venue
- Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security
- Publisher
- ACM
- Published
- 2021-11-12
- Pages
- 880-895
- OpenAlex
- W3214437258
- Cited by
- 184
- References
- 21
- FWCI
- 16.66
- Type
- conference paper
- Language
- en
- Open access
- closed
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.