The DOI matches its Crossref record; 44 of the 47 references it cites were found in a registry or an index.
Privacy-Enhanced Federated Learning Against Poisoning Adversaries
Abstract
Federated learning (FL), as a distributed machine learning setting, has received considerable attention in recent years. To alleviate privacy concerns, FL essentially promises that multiple parties jointly train the model by exchanging gradients rather than raw data. However, intrinsic privacy issue still exists in FL, e.g., user’s training samples could be revealed by solely inferring gradients. Moreover, the emerging poisoning attack also poses a crucial security threat to FL. In particular, due to the distributed nature of FL, malicious users may submit crafted gradients during the training process to undermine the integrity and availability of the model. Furthermore, there exists a contradiction in simultaneously addressing two issues, that is, privacy-preserving FL solutions are dedicated to ensuring gradients indistinguishability, whereas the defenses against poisoning attacks tend to remove outliers based on their similarity. To solve such a dilemma, in this paper, we aim to build a bridge between the two issues. Specifically, we present a privacy-enhanced FL (PEFL) framework that adopts homomorphic encryption as the underlying technology and provides the server with a channel to punish poisoners via the effective gradient data extraction of the logarithmic function. To the best of our knowledge, the PEFL is the first effort to efficiently detect the poisoning behaviors in FL under ciphertext. Detailed theoretical analyses illustrate the security and convergence properties of the scheme. Moreover, the experiments conducted on real-world datasets show that the PEFL can effectively defend against label-flipping and backdoor attacks, two representative poisoning attacks in FL.
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
“To solve this problem, [38], [49], [51] used homomorphic encryption to evaluate the local model securely.”
From Poisoning attacks in federated learning: A survey (2023) · cites this paper as [51]
Citations
Cites
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
Public-Key Cryptosystems Based on Composite Degree Residuosity Classes
Paillier, P. (2007) · Lecture Notes in Computer Science · doi:10.1007/3-540-48910-x_16 · Cited by 7,250
Deep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578
ADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322
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
Pearson Correlation Coefficient
Benesty, J., Chen, J., Huang, Y. A., & Cohen, I. (2009) · Springer topics in signal processing · doi:10.1007/978-3-642-00296-0_5 · Cited by 3,540
Privacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356
On the momentum term in gradient descent learning algorithms
Ning Qian, A. (1999) · Neural Networks · doi:10.1016/s0893-6080(98)00116-6 · Cited by 2,318
SecureML: A System for Scalable Privacy-Preserving Machine Learning
Mohassel, P., & Zhang, Y. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.12 · Cited by 1,936
Nasr, M., Shokri, R., & Houmansadr, A. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00065 · Cited by 1,760
Cited by
Sorted by citations
Li, Y., Jiang, Y., Li, Z., & Xia, S.-T. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3182979 · Cited by 682
“In contrast, some works [30], [101]–[103] also questioned whether federal learning is really easy to be attacked.”
ResultA robust privacy-preserving federated learning model against model poisoning attacks
Yazdinejad, A., Dehghantanha, A., Karimipour, H., Srivastava, G., & Parizi, R. M. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3420126 · Cited by 380
“Model poisoning adversaries manipulate user input by submitting poisonous updates to local models to create arbitrary deviance from correct trends [3].”
BackgroundMethodInfluentialShieldFL: Mitigating Model Poisoning Attacks in Privacy-Preserving Federated Learning
Ma, Z., Ma, J., Miao, Y., Li, Y., & Deng, R. H. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3169918 · Cited by 371
Blockchain-Based Federated Learning for Securing Internet of Things: A Comprehensive Survey
Issa, W., Moustafa, N., Turnbull, B., Sohrabi, N., & Tari, Z. (2022) · ACM Computing Surveys · doi:10.1145/3560816 · Cited by 347
“In addition, Truex et al. [144] and Xu et al. [164] combined SMC and DP for FL privacy preservation.”
BackgroundMethodInfluentialPrivacy-Preserving Byzantine-Robust Federated Learning via Blockchain Systems
Miao, Y., Liu, Z., Li, H., Choo, K.-K. R., & Deng, R. H. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3196274 · Cited by 303
Self-citation
Metadata
- Authors
- Liu, X., Li, H., Xu, G., Chen, Z., Huang, X., & Lu, R.
- Affiliations
- University of Electronic Science and Technology of China (CN)
- Nanyang Technological University (SG)
- China Electronics Technology Group Corporation (CN)
- University of New Brunswick (CA)
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2021
- Volume
- 16
- Pages
- 4574-4588
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W3198262235
- Cited by
- 351
- References
- 47
- Citations by year
- 2026: 47 · 2025: 102 · 2024: 110 · 2023: 66 · 2022: 23 · 2021: 3
- FWCI
- 17.85
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Information Forensics and Security (publishedVersion)
- DR-NTU (Nanyang Technological University) (submittedVersion)
- Funders
- National Natural Science Foundation of China (62020106013, 61972454, 61802051, 61772121, 61728102)
- Sichuan Science and Technology Program (2020JDTD0007, 2020YFG0298)
- Chongqing Science and Technology Commission (cstc2018jcyjAX0703)
- Fundamental Research Funds for Chinese Central Universities (ZYGX2020ZB027)
- 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 Networks and Communications › Cryptography and Data Security
- Keywords
- privacy-preserving federated learning, poisoning attacks, homomorphic encryption, gradient privacy, poisoning detection, label-flipping attacks, backdoor 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
