Secure Partial Aggregation: Making Federated Learning More Robust for Industry 4.0 Applications
Abstract
Big data, due to its promotion for industrial intelligence, has become the cornerstone of the Industry 4.0 era.Federated learning, proposed by Google, can effectively integrate data from different devices and different domains to train models under the premise of privacy preservation. Unfortunately, this new training paradigm faces security risks both on the client side and server side. This article proposes a new federated learning scheme to defend from client-side malicious uploads (e.g., backdoor attacks). In addition, we use cryptography techniques to prevent server-side privacy attacks (e.g., membership inference). Thesecure partial aggregationprotocol we designed improves the privacy and robustness of federated learning. The experiments show that models can achieve high accuracy of over 90% with a proper upload proportion, while the accuracy of the backdoor attack decreased from 99.5% to 0% with the best result. Meanwhile, we prove that our protocol can disable privacy attacks.
Integrity signals
Registry
Cites
Statistics
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?
PartFedAvg is a new aggregation protocol proposed to defend against data poisoning attacks.
“In [204], a new aggregation protocol, PartFedAvg, is proposed to defend against data poisoning attacks.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [204]
PartFedAvg ensures the privacy of the participants involved.
“The proposed method ensures the privacy of the participants involved.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [204]
PartFedAvg improves the robustness of the global model because the malicious attacker cannot inject completed backdoor patterns in a short time.
“The malicious attacker cannot inject completed backdoor patterns in a short time, thus improving the robustness of the global model.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [204]
The methods in [204] and [205] require the number of malicious attacks to be smaller than 50% of the total selected clients in each round.
“The method requires the number of malicious attacks to be smaller than 50% of the total selected clients in each round.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [204]
The defense schemes in [204] and [205] require modifying the local training process, and the backdoor effect can only be suppressed and cannot be entirely eliminated.
“The defense schemes proposed in [204] and [205] require modifying the local training process, and the backdoor effect can only be suppressed and cannot be entirely eliminated.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [204]
Cites
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 · see citing works
Federated Learning: Strategies for Improving Communication Efficiency
Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016) · arXiv · doi:10.48550/arxiv.1610.05492 · Cited by 3,766 · see citing works
Industrial Internet of Things: Challenges, Opportunities, and Directions
Sisinni, E., Saifullah, A., Han, S., Jennehag, U., & Gidlund, M. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2852491 · Cited by 2,380 · see citing works
Zhu, L., & Han, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_2 · Cited by 1,906 · see citing works
Exploiting Unintended Feature Leakage in Collaborative Learning
Melis, L., Song, C., De Cristofaro, E., & Shmatikov, V. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00029 · Cited by 1,734 · see citing works
On the Convergence of FedAvg on Non-IID Data
Li, X., Huang, K., Yang, W., Wang, S., & Zhang, Z. (2019) · arXiv · doi:10.48550/arxiv.1907.02189 · Cited by 1,575 · see citing works
How to backdoor federated learning
Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V. (2018) · arXiv · doi:10.48550/arxiv.1807.00459 · Cited by 1,495 · see citing works
(2017) · neural information processing systems · Cited by 1,413 · see citing works
Multiparty Computation from Somewhat Homomorphic Encryption
Damgård, I., Pastro, V., Smart, N., & Zakarias, S. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-32009-5_38 · Cited by 1,331 · see citing works
BadNets: Evaluating Backdooring Attacks on Deep Neural Networks
Gu, T., Liu, K., Dolan-Gavitt, B., & Garg, S. (2019) · IEEE Access · doi:10.1109/access.2019.2909068 · Cited by 1,238 · see citing works
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Yin, D., Chen, Y., Ramchandran, K., & Bartlett, P. (2018) · arXiv · doi:10.48550/arxiv.1803.01498 · Cited by 1,130 · see citing works
Somewhat Practical Fully Homomorphic Encryption.
Fan, J., & Vercauteren, F. (2012) · Cited by 1,011 · see citing works
iDLG: Improved Deep Leakage from GradientsPreprint
Zhao, B., Mopuri, K. R., & Bilen, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.02610 · Cited by 575 · see citing works
Deploying Fog Computing in Industrial Internet of Things and Industry 4.0
Aazam, M., Zeadally, S., & Harras, K. A. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2855198 · Cited by 572 · see citing works
DBA: Distributed Backdoor Attacks against Federated Learning
Xie, C., Huang, K., Chen, P., & Li, B. (2020) · International Conference on Learning Representations · Cited by 468 · see citing works
Federated Learning for intrusion detection system: Concepts, challenges and future directions
Agrawal, S., Sarkar, S., Aouedi, O., Yenduri, G., Piamrat, K., Alazab, M., Bhattacharya, S., Maddikunta, P. K. R., & Gadekallu, T. R. (2022) · Computer Communications · doi:10.1016/j.comcom.2022.09.012 · Cited by 457 · see citing works
VeriFL: Communication-Efficient and Fast Verifiable Aggregation for Federated Learning
Guo, X., Liu, Z., Li, J., Gao, J., Hou, B., Dong, C., & Baker, T. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3043139 · Cited by 319 · see citing works
Self-citationOverdrive: Making SPDZ Great Again
Keller, M., Pastro, V., & Rotaru, D. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-78372-7_6 · Cited by 291 · see citing works
Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted HardwarePreprint
Tramèr, F., & Boneh, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.03287 · Cited by 263 · see citing works
Communication-Efficient Federated Learning With Compensated Overlap-FedAvg
Zhou, Y., Ye, Q., & Lv, J. (2021) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2021.3090331 · Cited by 237 · see citing works
Deep Models Under the GAN: Information Leakage from Collaborative Deep LearningPreprint
Hitaj, B., Ateniese, G., & Pérez‐Cruz, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.07464 · Cited by 232 · see citing works
Anonymous and Privacy-Preserving Federated Learning With Industrial Big Data
Zhao, B., Fan, K., Yang, K., Wang, Z., Li, H., & Yang, Y. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3052183 · Cited by 169 · see citing works
Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning
Agrawal, S., Sarkar, S., Alazab, M., Maddikunta, P. K. R., Gadekallu, T. R., & Pham, Q. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/7156420 · Cited by 72 · see citing works
Industrial Cyber-Physical Systems-Based Cloud IoT Edge for Federated Heterogeneous Distillation
Wang, C., Yang, G., Papanastasiou, G., Zhang, H., Rodrigues, J. J. P. C., & de Albuquerque, V. H. C. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3007407 · Cited by 67 · see citing works
Using TopGear in Overdrive: A More Efficient ZKPoK for SPDZ
Baum, C., Cozzo, D., & Smart, N. P. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-38471-5_12 · Cited by 53 · see citing works
Overdrive2k: Efficient Secure MPC over $$\mathbb {Z}_{2^k}$$ from Somewhat Homomorphic Encryption
Orsini, E., Smart, N. P., & Vercauteren, F. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-40186-3_12 · Cited by 31 · see citing works
Adding Distributed Decryption and Key Generation to a Ring-LWE Based CCA Encryption Scheme
Smart, N., Michael, K., Lindell, Y., et al. (2019) · Lirias · doi:10.1007/978-3-030-21548-4\_11 · Cited by 19 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Wan, Y., Qu, Y., Ni, W., Xiang, Y., Gao, L., & Hossain, E. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3361451 · Cited by 152 · see citing works
“Limitations: The defense schemes proposed in [204] and [205] require modifying the local training process, and the backdoor effect can only be suppressed and cannot be entirely eliminated.”
BackgroundMethod
- Authors
- Gao, J., Zhang, B., Guo, X., Baker, T., Li, M., & Liu, Z.
- Affiliations
- Nankai University (CN)
- University of Sharjah (AE)
- Venue
- IEEE Transactions on Industrial Informatics
- Published
- 2022-09
- Volume
- 18
- Issue
- 9
- Pages
- 6340-6348
- ISSN
- 1551-3203 (ISSN-L)
- 1941-0050
- OpenAlex
- W4210508597
- Cited by
- 41
- References
- 27
- Citations by year
- 2026: 9 · 2025: 10 · 2024: 10 · 2023: 9 · 2022: 3
- FWCI
- 2.63
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Industrial Informatics (publishedVersion)
- University of Brighton Repository (University of Brighton) (submittedVersion)
- Funders
- National Natural Science Foundation of China (62032012)
- National Key Research and Development Program of China (2020YFB1005700)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Cryptography and Data Security
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- federated learning, backdoor attacks, membership inference attacks, privacy preservation, Industry 4.0, industrial data security
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
