Efficiency Optimization Techniques in Privacy-Preserving Federated Learning With Homomorphic Encryption: A Brief Survey
The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Abstract
Federated learning (FL) offers distributed machine learning on edge devices. However, the FL model raises privacy concerns. Various techniques, such as homomorphic encryption (HE), differential privacy, and multiparty cooperation, are used to address the privacy issues of the FL model. Among them, HE ensures greater security and privacy since end-to-end encryption maintains data privacy throughout the computation process. Compared with other privacy-preserving techniques, HE does not require the establishment of a trusted environment or protocol among multiple parties and does not involve any artificial noise that can impair system performance. Unfortunately, it suffers from efficiency overhead when applied to privacy-preserving FL (PPFL). Some existing surveys on PPFL discuss the generic construction and organization of PPFL from the perspective of practical HE deployment in PPFL. However, none of them covers the efficiency optimization of HE when applied to PPFL. This article conducts a comprehensive review of the efficiency optimization of HE when applied to PPFL. First, we review general optimization strategies and discuss their limitations when applied directly to HE-based PPFL. Second, an overview of algorithmic, hardware, and hybrid optimizations is provided, along with a discussion of their adaptation. Additionally, we provide a detailed taxonomy of optimizations. Finally, we suggest future HE-based PPFL research directions.
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
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 · cited 1×
“FL can also be categorized into “cross-device” and “cross-silo” settings [52].”
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
Fully homomorphic encryption using ideal lattices
Gentry, C. (2009) · Proceedings of the forty-first annual ACM symposium on Theory of computing · doi:10.1145/1536414.1536440 · Cited by 6,806 · cited 1×
“Another line of study of existing defense in PPFL is homomorphic encryption (HE) [29], [30], [31], [32], which offers a robust post-quantum solution that counteracts privacy attacks while maintaining the full utility of aggregated models.”
BackgroundFederated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
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 · cited 2×
“MPC enables the involved parties to jointly compute a mutual function to aggregate the local models, i.e., garbled circuit (GC) [23], Masking [19] and secret sharing (SS) [24], [25].”
BackgroundPolynomial-time algorithms for prime factorization and discrete logarithms on a quantum computer
Shor, P. W. (1999) · SIAM Review · doi:10.1137/s0036144598347011 · Cited by 3,904
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
Homomorphic Encryption for Arithmetic of Approximate Numbers
Cheon, J. H., Kim, A., Kim, M., & Song, Y. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-70694-8_15 · Cited by 2,522 · cited 3×
“The first class contains BGV [55], BFV [56] and CKKS [30], where BGV and BFV perform exact operations on integers, and CKKS supports approximate computations over real and complex numbers.”
BackgroundMethodFederated Learning With Differential Privacy: Algorithms and Performance Analysis
Wei, K., Li, J., Ding, M., Ma, C., Yang, H. H., Farokhi, F., Jin, S., Quek, T. Q. S., & Vincent Poor, H. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.2988575 · Cited by 2,400 · cited 1×
“In particular, existing defenses in PPFL to counteract the privacy attacks include multiparty computation (MPC) [19], [20] and differential privacy (DP) [21], [22].”
BackgroundPrivacy-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 · cited 1×
“Several approaches [28], [49], [59] have been proposed to achieve this, including the use of PHE schemes, such as Paillier [53].”
MethodOptimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks
Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., & Cong, J. (2015) · Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/2684746.2689060 · Cited by 2,158 · cited 1×
“FPGAs have been employed in diverse fields, including traditional machine learning [111] and cryptography [112].”
MethodNasr, M., Shokri, R., & Houmansadr, A. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00065 · Cited by 1,760
Hubara, I., Soudry, D., & Yaniv, R. E. (2016) · arXiv · doi:10.48550/arxiv.1602.02505 · Cited by 1,667
Privacy-Preserving Deep Learning via Additively Homomorphic Encryption
Phong, L. T., Aono, Y., Hayashi, T., Wang, L., & Moriai, S. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2787987 · Cited by 1,662
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Hitaj, B., Ateniese, G., & Perez-Cruz, F. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134012 · Cited by 1,377 · cited 2×
“…[15], [16], [17], [18] have been proposed, allowing the curious server and malicious clients to extract privacy-sensitive information in the training data, including membership inference attacks [12], [13], [14], inversion attacks [15], [16], [17] and private attribute extraction attacks [18].”
BackgroundBeyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
Wang, Z., Song, M., Zhang, Z., Song, Y., Wang, Q., & Qi, H. (2019) · IEEE INFOCOM 2019 - IEEE Conference on Computer Communications · doi:10.1109/infocom.2019.8737416 · Cited by 881
SecureBoost: A Lossless Federated Learning Framework
Cheng, K., Fan, T., Jin, Y., Liu, Y., Chen, T., Papadopoulos, D., & Yang, Q. (2021) · IEEE Intelligent Systems · doi:10.1109/mis.2021.3082561 · Cited by 669
SecureBoost: A Lossless Federated Learning Framework
Cheng, K., Fan, T., Jin, Y., Liu, Y., Chen, T., Papadopoulos, D., & Yang, Q. (2019) · arXiv · doi:10.48550/arxiv.1901.08755 · Cited by 668
Yin, X., Zhu, Y., & Hu, J. (2022) · ACM Computing Surveys · doi:10.1145/3460427 · Cited by 638 · cited 2×
“Currently, several existing surveys in [40], [41], [42], [43], [44], and [45] extensively analyze privacy and security threats to FL systems with discussions on potential attacks and defenses.”
BackgroundFederated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · arXiv · doi:10.48550/arxiv.1902.04885 · Cited by 600
Privacy and Robustness in Federated Learning: Attacks and Defenses
Lyu, L., Yu, H., Ma, X., Chen, C., Sun, L., Zhao, J., Yang, Q., & Yu, P. S. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3216981 · Cited by 548 · cited 2×
“Currently, several existing surveys in [40], [41], [42], [43], [44], and [45] extensively analyze privacy and security threats to FL systems with discussions on potential attacks and defenses.”
BackgroundHardy, S., Henecka, W., Ivey-Law, H., Nock, R., Patrini, G., Smith, G., & Thorne, B. (2017) · arXiv · doi:10.48550/arxiv.1711.10677 · Cited by 431 · cited 3×
“2) HE-Based VFL: Distinct from horizontal partitioned data, in VFL, participating clients accomplish model training interactively by performing computations and exchanging encrypted intermediate results without revealing original data [49], [61], [62].”
BackgroundMethodShieldFL: 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
Federated learning in a medical context: A systematic literature review
Pfitzner, B., Steckhan, N., & Arnrich, B. (2021) · ACM Transactions on Internet Technology · doi:10.1145/3412357 · Cited by 288 · cited 1×
“For example, multiple medical institutions, e.g., hospitals, own different records for the same patients [50], [51].”
BackgroundEvaluating Differentially Private Machine Learning in Practice
Jayaraman, B., & Evans, D. (2019) · arXiv · doi:10.48550/arxiv.1902.08874 · Cited by 265
Secure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation
Kim, M., Song, Y., Wang, S., Xia, Y., & Jiang, X. (2018) · JMIR Medical Informatics · doi:10.2196/medinform.8805 · Cited by 257 · cited 2×
“By applying their GPU implementation to train a logistic regression model, they achieved a significant speedup of 40 × compared to an 8-threaded CPU implementation [115], [116].”
MethodPrivacy-Preserving Patient Similarity Learning in a Federated Environment: Development and Analysis
Lee, J., Sun, J., Wang, F., Wang, S., Jun, C.-H., & Jiang, X. (2018) · JMIR Medical Informatics · doi:10.2196/medinform.7744 · Cited by 196 · cited 1×
“For example, multiple medical institutions, e.g., hospitals, own different records for the same patients [50], [51].”
BackgroundPOSEIDON: Privacy-Preserving Federated Neural Network Learning
Sav, S., Pyrgelis, A., Troncoso-Pastoriza, J. R., Froelicher, D., Bossuat, J.-P., Sousa, J. S., & Hubaux, J.-P. (2021) · Proceedings 2021 Network and Distributed System Security Symposium · doi:10.14722/ndss.2021.24119 · Cited by 162
EPPDA: An Efficient Privacy-Preserving Data Aggregation Federated Learning Scheme
Song, J., Wang, W., Gadekallu, T. R., Cao, J., & Liu, Y. (2023) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3153519 · Cited by 150 · cited 1×
“MPC enables the involved parties to jointly compute a mutual function to aggregate the local models, i.e., garbled circuit (GC) [23], Masking [19] and secret sharing (SS) [24], [25].”
BackgroundIBM Federated Learning: an Enterprise Framework White Paper V0.1
Ludwig, H., Baracaldo, N., Thomas, G., Zhou, Y., Anwar, A., Rajamoni, S., Ong, Y., Radhakrishnan, J., Verma, A., Sinn, M., et al. (2020) · arXiv · doi:10.48550/arxiv.2007.10987 · Cited by 106
Boosting Privately: Federated Extreme Gradient Boosting for Mobile Crowdsensing
Liu, Y., Ma, Z., Liu, X., Ma, S., Nepal, S., Deng, R. H., & Ren, K. (2020) · 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs47774.2020.00017 · Cited by 93 · cited 1×
“FEDXGB [119] involves a new HE-based secure aggregation scheme for FL.”
MethodBlockchain-Based Personalized Federated Learning for Internet of Medical Things
Lian, Z., Wang, W., Han, Z., & Su, C. (2023) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2023.3279111 · Cited by 75 · cited 1×
“IoT devices allow real-time monitoring of patient health [3], [4], irrigation systems in agriculture, smart financial systems, and streamlined industrial operations.”
BackgroundCOFEL: Communication-Efficient and Optimized Federated Learning with Local Differential Privacy
Lian, Z., Wang, W., & Su, C. (2021) · ICC 2021 - IEEE International Conference on Communications · doi:10.1109/icc42927.2021.9500632 · Cited by 58
ECRT: An Edge Computing System for Real-Time Image-based Object Tracking
Zhao, Z., Jiang, Z., Ling, N., Shuai, X., & Xing, G. (2018) · Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems · doi:10.1145/3274783.3275199 · Cited by 39 · cited 1×
“This intelligence can then be used to support AI-powered applications, ranging from virtual reality to e-commerce [6].”
Self-citationLayer-Based Communication-Efficient Federated Learning with Privacy Preservation
LIAN, Z., WANG, W., HUANG, H., & SU, C. (2022) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2021bcp0006 · Cited by 33 · cited 1×
“Previous work on privacy leakage analysis shows that the partial transparency , e.g., hiding parts of the models [83], [84], [85], can grant the adversary a limited chance to successfully perform attacks like gradient inversion privacy attacks [15].”
BackgroundEfficient Federated Matrix Factorization Against Inference Attacks
Chai, D., Wang, L., Chen, K., & Yang, Q. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3501812 · Cited by 20 · cited 1×
“Chai et al. [105] proposed an efficient federated matrix factorization method that protects users against inference attacks in FL.”
Method
Metadata
- Authors
- Xie, Q., Jiang, S., Jiang, L., Huang, Y., Zhao, Z., Khan, S., Dai, W., Liu, Z., & Wu, K.
- Venue
- IEEE Internet of Things Journal
- Published
- 2024-07-15
- Volume
- 11
- Issue
- 14
- Pages
- 24569-24580
- ISSN
- 2327-4662 (ISSN-L)
- 2372-2541
- OpenAlex
- W4400409839
- Cited by
- 191
- References
- 36
- FWCI
- 28.28
- Type
- journal article
- 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.