Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
Open accessThe DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Abstract
Federated learning, i.e., a mobile edge computing framework for deep learning, is a recent advance in privacy-preserving machine learning, where the model is trained in a decentralized manner by the clients, i.e., data curators, preventing the server from directly accessing those private data from the clients. This learning mechanism significantly challenges the attack from the server side. Although the state-of-the-art attacking techniques that incorporated the advance of Generative adversarial networks (GANs) could construct class representatives of the global data distribution among all clients, it is still challenging to distinguishably attack a specific client (i.e., user-level privacy leakage), which is a stronger privacy threat to precisely recover the private data from a specific client. This paper gives the first attempt to explore user-level privacy leakage against the federated learning by the attack from a malicious server. We propose a framework incorporating GAN with a multi-task discriminator, which simultaneously discriminates category, reality, and client identity of input samples. The novel discrimination on client identity enables the generator to recover user specified private data. Unlike existing works that tend to interfere the training process of the federated learning, the proposed method works “invisibly” on the server side. The experimental results demonstrate the effectiveness of the proposed attacking approach and the superior to the state-of-the-art.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“By definition, FL systems avoid sharing healthcare data among participating institutions.”
From The future of digital health with federated learning (2020) · cites this paper as [62]
In the citing paper
“Deidentified data may become identifiable during the data collection and processing phase, and confidential proprietary medical information, such as drug development and treatment plans, may be inferred during the data collection and processing phase [76], leading to data and privacy breaches.”
From Generative AI in medical practice: in-depth exploration of privacy and security challenges (2024) · cites this paper as [76]
In the citing paper
“In particular, private data can be extracted indirectly even from the shared information, by means of some emerging techniques, such as model inversion of the model updates [56], gradients themselves [57] and adversarial attacks [58].”
From Handling privacy-sensitive medical data with federated learning: Challenges and future directions (2023) · cites this paper as [58]
In the citing paper
“Federated learning promises to protect the privacy of local user data, however, recent studies have shown that the involvement of specific participants can still be revealed by analyzing the global model [165].”
From Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental Analysis (2021) · cites this paper as [165]
Citations
Cites
Labaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Improved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557
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
Practical Secure Aggregation for Privacy-Preserving Machine Learning
Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3133982 · Cited by 3,956
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
Fredrikson, M., Jha, S., & Ristenpart, T. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813677 · Cited by 2,961
Research works printed but not linked: 1
- yann, 1998, The most database of handwritten digits
Cited by
Items 901–927 of 927
Vasan, S. S., & Jayalakshmi, P. (2026) · IEEE Access · doi:10.1109/access.2026.3683070
Heterogeneous Privacy-Preserving Federated Learning for Edge Intelligence
Zhang, Z., WU, L., Cui, H., Wang, Z., Huo, L., Wang, J., & Hu, S. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3685129 · Cited by 1
Self-citationHow Can We Keep the Right to be Forgotten? ORAFL: One Round Aggregation Scheme for FL
Fan, Y., Zhang, W., Shang, W.-Q., Li, K. C., & Zhu, H.-B. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3688514
Ding, S., Yuan, X., Wang, Z., Zhang, L. E., & Ateniese, G. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00070
Self-citationLost in the Averages: Reassessing Record-Specific Privacy Risk Evaluation
Krčo, N., Guépin, F., Meeus, M., Kulynych, B., & de Montjoye, Y.-A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-16089-8_2
Li, K., Yuan, X., & Ni, W. (2026) · Springer series in reliability engineering · doi:10.1007/978-3-032-23959-4_6
Galende, B. A., Apellániz, P. A., Almodóvar, A., Uribe, S., Álvarez, F., & Parras, J. (2026) · Big Data and Cognitive Computing · doi:10.3390/bdcc10050163
XAI-Driven Input Masking to Mitigating Model Inversion Attacks
Sani, S. D., Faiyaz, A., & Salman, T. (2026) · IEEE International Conference on Secure IoT, Assured and Trusted Computing (SATC) · doi:10.1109/satc69565.2026.11542488
FedGB: A Generator-Based Federated Learning Against Reconstruction Attacks
Sandouka, S. B., & Felemban, M. (2026) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2026.3700901
Sun, H., Wu, L., Wang, Z., Li, B., Zhuang, H., Wang, W., Deng, Y., Li, M., & Zhang, H. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810704
Self-citationDmello, L., D’Mello, B., & Tuscano, L. (2026) · Research Square · doi:10.21203/rs.3.rs-9273318/v1
Dynamic Noise Injection for Gradient Leakage Resistance in Federated Learning
Thonglek, K., Pandee, K., Namlao, I., & Toopprasom, P. (2025) · Asian Conference on Communication and Networks (ASIANComNet) · doi:10.1109/asiancomnet68615.2025.11579572
Fed-CEP: Federated Causal-Semantic Privacy via Calibrated Input Perturbation
Cui, Q., Zhao, D., Tan, Z., Lv, M., Dang, P., Liu, X., Guo, M., Wang, H., & Li, H. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11581530
Enhancing Medical Diagnostics with Federated Learning: Secure Model Aggregation Across Hospitals
Ghanta, S., Yarra, K., Kancharla, L., Kondapaneni, K., Boreddy, D., Boyapati, P., & Pradhan, A. K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-19981-2_26
Communication-efficient Federated Graph Classification via Generative Diffusion Modeling
Wang, X., Huang, X. S., Hu, H., & Xu, J. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3780262
Privacy-preserving distributed artificial intelligence in connectionism-based models
Barco, I. A. (2024) · RIO (Universidad Pablo de Olavide)
SecureFed-AI: Byzantine-Robust Federated Learning for Non-IID Sentiment Analysis
Khudier, D. T., Abbas, N. M., & Abdulhadi, M. T. (2026) · International Journal of Safety and Security Engineering · doi:10.18280/ijsse.160709
Halenka, V., Amini, M., Andersen, P.-A., Granmo, O.-C., Jiao, L., & Kantarci, B. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3727545
Bounding User Contributions for User-Level Differentially Private Mean Estimation
Rameshwar, V. A., & Tandon, A. (2026) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit62367.2026.11653691
Trusted Asynchronous Federated Learning Based on DAG Blockchain
Liu, C., & Wu, X. (2026) · doi:10.1145/3821820.3821825
A Privacy Protection Method for Vehicle Networking Based on Heterogeneous Aggregation Signcryption
Yan, C., Elkhalil, A., Zhu, Y., Cui, Y., Yan, S., & Dong, H. (2026) · International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC) · doi:10.1109/aiotc71250.2026.11688481
FedFD: Semantics-Guided Feature Diffusion for Federated Learning with Private Extractors
Hong, Y., Zheng, Y., Hu, K., Tang, P., & Qiu, W. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5737-9_2
Security and Privacy in Federated Learning
Lu, X., Yan, C., Liò, P., Hui, P., & Wang, P. (2026) · IntechOpen eBooks · doi:10.5772/intechopen.1017100
Security-Enhanced and Privacy-Preserving Federated Learning
Chu, T. (2025) · IMDEA Networks Institute Digital Repository
Blockchain-based distributed federated learning using proof of accuracy consensus
Bidgoly, A. J., & Bidgoly, A. J. (2026) · Soft Computing · doi:10.1007/s00500-026-11492-8
Anas, H., Toumi, H., & Talea, M. (2026) · Sakarya University Journal of Computer and Information Sciences · doi:10.35377/saucis...1826274
Astuti, S., Pramudita, A. A., Dewanta, F., & Istikmal (2026) · International Conference on Wireless and Telematics (ICWT) · doi:10.1109/icwt71445.2026.11751566
Metadata
- Authors
- Wang, Z., Song, M., Zhang, Z., Song, Y., Wang, Q., & Qi, H.
- Affiliations
- Wuhan University (CN)
- University of Tennessee at Knoxville (US)
- Venue
- IEEE INFOCOM 2019 - IEEE Conference on Computer Communications
- Publisher
- IEEE
- Published
- 2019-04
- Pages
- 2512-2520
- OpenAlex
- W2964162474
- Cited by
- 881
- References
- 23
- Citations by year
- 2026: 47 · 2025: 107 · 2024: 190 · 2023: 173 · 2022: 146 · 2021: 129 · 2020: 78 · 2019: 11
- FWCI
- 34.81
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Conference on Computer Communications (INFOCOM) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- federated learning, malicious server attacks, generative adversarial networks, class representatives, privacy-preserving machine learning, data reconstruction attacks
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.