Decentralized Federated Learning: A Survey on Security and Privacy
Open accessThe DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.
Abstract
Federated learning has been rapidly evolving and gaining popularity in recent years due to its privacy-preserving features, among other advantages. Nevertheless, the exchange of model updates and gradients in this architecture provides new attack surfaces for malicious users of the network which may jeopardize the model performance and user and data privacy. For this reason, one of the main motivations for decentralized federated learning is to eliminate server-related threats by removing the server from the network and compensating for it through technologies such as blockchain. However, this advantage comes at the cost of challenging the system with new privacy threats. Thus, performing a thorough security analysis in this new paradigm is necessary. This survey studies possible variations of threats and adversaries in decentralized federated learning and overviews the potential defense mechanisms. Trustability and verifiability of decentralized federated learning are also considered in this study.
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
Shamir, A. (1979) · Communications of the ACM · doi:10.1145/359168.359176 · Cited by 13,756 · cited 1×
“Biscotti [5] couples DP with a secure aggregation technique [111] to safeguard DFL systems against poisoning and inference attacks.”
MethodA method for obtaining digital signatures and public-key cryptosystems
Rivest, R. L., Shamir, A., & Adleman, L. (1978) · Communications of the ACM · doi:10.1145/359340.359342 · Cited by 13,462
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
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 2×
“While full HE offers greater flexibility, it is inefficient when compared to other forms of HE [97].”
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
Self-citationFederated learning: Challenges, methods, and future directions
Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.2975749 · Cited by 6,210 · cited 1×
“Relying on Peer-to-Peer (P2P) communications, Decentralized Federated Learning (DFL) improves both the reliability and scalability of FL by eliminating SPF and enhancing the communication efficiency [6], [7].”
BackgroundMembership 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 1×
“Regularization techniques such as L 2 regularizer [146] and dropout [147] can eliminate the effect of such malicious samples to a great extent.”
MethodFederated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023
Hyperledger fabric: a distributed operating system for permissioned blockchains
Androulaki, E., Barger, A., Bortnikov, V., Cachin, C., Christidis, K., De Caro, A., Enyeart, D., Ferris, C., Laventman, G., Manevich, Y., et al. (2018) · Proceedings of the Thirteenth EuroSys Conference · doi:10.1145/3190508.3190538 · Cited by 3,654
Differential Privacy: A Survey of Results
Dwork, C. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-79228-4_1 · Cited by 3,542 · cited 1×
“DPin[54]isimplementedthroughperturbing localgradientsusingtheexponentialmechanism[112]andapre-definedprobabilitydensityfunctionbeforeuploadingtheminto theblockchainandbroadcastingthemacrosstheDFLnetwork.”
IoT security: Review, blockchain solutions, and open challenges
Khan, M. A., & Salah, K. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2017.11.022 · Cited by 2,488 · cited 1×
“3) Routing Attacks: Reliable network infrastructure is of paramount importance for DFL due to its integration with blockchain [72], [73].”
BackgroundSecureML: 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 · cited 1×
“For instance, SMC was used in [105] for private model training.”
MethodZhu, L., & Han, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_2 · Cited by 1,906
Our Data, Ourselves: Privacy Via Distributed Noise Generation
Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., & Naor, M. (2006) · Lecture Notes in Computer Science · doi:10.1007/11761679_29 · Cited by 1,835 · cited 2×
“The concept of distributed DP alludes to the notion that the required amount of noise is derived from several individuals [122].”
BackgroundA Survey on the Security of Blockchain Systems
Li, X., Jiang, P., Chen, T., Luo, X., & Wen, Q. (2020) · Future Generation Computer Systems · doi:10.1016/j.future.2017.08.020 · Cited by 1,772 · cited 1×
“As the name implies, the latter aims at degrading the performance of all classes in general whereas the targeted scheme only attacks a certain class without tampering with the rest of the model [16].”
BackgroundExploiting 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
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
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 · cited 2×
“As the name implies, the latter aims at degrading the performance of all classes in general whereas the targeted scheme only attacks a certain class without tampering with the rest of the model [16].”
BackgroundA survey on security and privacy of federated learning
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.10.007 · Cited by 1,480
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
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 · cited 1×
“This is while partially HE can only execute one operation (e.g., addition or multiplication), and substantially HE can do several operations [98], [99], [100].”
BackgroundConsortium Blockchain for Secure Energy Trading in Industrial Internet of Things
Li, Z., Kang, J., Yu, R., Ye, D., Deng, Q., & Zhang, Y. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2786307 · Cited by 1,103
Blockchained On-Device Federated Learning
Kim, H., Park, J., Bennis, M., & Kim, S.-L. (2020) · IEEE Communications Letters · doi:10.1109/lcomm.2019.2921755 · Cited by 887 · cited 1×
“For instance, BlockFL [150] verifies the submitted updates through a random selection of workers before letting the update take effect.”
BackgroundSwarm Learning for decentralized and confidential clinical machine learning
Warnat-Herresthal, S., Schultze, H., Shastry, K. L., Manamohan, S., Mukherjee, S., Garg, V., Sarveswara, R., Händler, K., Pickkers, P., Aziz, N. A., et al. (2021) · Nature · doi:10.1038/s41586-021-03583-3 · Cited by 884 · cited 2×
“Addressing these challenges requires ongoing research and adaptation of privacy-preserving techniques to suit the specific requirements of DFL. Developing optimized implementations of cryptographic methods, such as SMC, can help alleviate the computational overhead and address sensitivity concerns.”
BackgroundMethodBlockchained On-Device Federated Learning
Kim, H., Park, J., Bennis, M., & Kim, S.-L. (2018) · arXiv · doi:10.48550/arxiv.1808.03949 · Cited by 882
Pinocchio: Nearly Practical Verifiable Computation
Parno, B., Howell, J., Gentry, C., & Raykova, M. (2013) · 2013 IEEE Symposium on Security and Privacy · doi:10.1109/sp.2013.47 · Cited by 864
Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
Jagielski, M., Oprea, A., Biggio, B., Liu, C., Nita-Rotaru, C., & Li, B. (2018) · 2018 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2018.00057 · Cited by 861
Learning Differentially Private Recurrent Language Models
McMahan, H. B., Ramage, D., Talwar, K., & Zhang, L. (2017) · arXiv · doi:10.48550/arxiv.1710.06963 · Cited by 849
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
Self-citationSecureBoost: 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
Self-citationFederated learning meets blockchain in edge computing: Opportunities and challenges
Nguyen, D. C., Ding, M., Pham, Q.-V., Pathirana, P. N., Le, L. B., Seneviratne, A., Li, J., Niyato, D., & Poor, H. V. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3072611 · Cited by 661
A Blockchain-Based Decentralized Federated Learning Framework with Committee Consensus
Li, Y., Chen, C., Liu, N., Huang, H., Zheng, Z., & Yan, Q. (2021) · IEEE Network · doi:10.1109/mnet.011.2000263 · Cited by 645 · cited 3×
“At this scale, the attack is known as 51% attack in the literature [52].”
BackgroundMethodInfluentialA secure federated transfer learning framework
Liu, Y., Kang, Y., Xing, C., Chen, T., & Yang, Q. (2020) · IEEE Intelligent Systems · doi:10.1109/mis.2020.2988525 · Cited by 645
Self-citationSecure Federated Transfer Learning
Liu, Y., Kang, Y., Xing, C., Chen, T., & Yang, Q. (2018) · arXiv · doi:10.48550/arxiv.1812.03337 · Cited by 645
Self-citationSurvey on blockchain for Internet of Things
Wang, X., Zha, X., Ni, W., Liu, R. P., Guo, Y. J., Niu, X., & Zheng, K. (2019) · Computer Communications · doi:10.1016/j.comcom.2019.01.006 · Cited by 567
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 3×
“Malicious clients can follow different attack models to jeopar-dize the performance or privacy of the system [16].”
BackgroundSelf-citationSemi-supervised Knowledge Transfer for Deep Learning from Private Training Data
Papernot, N., Abadi, M., Erlingsson, Ú., Goodfellow, I., & Talwar, K. (2016) · arXiv · doi:10.48550/arxiv.1610.05755 · Cited by 492
Decentralized Privacy Using Blockchain-Enabled Federated Learning in Fog Computing
Qu, Y., Gao, L., Luan, T. H., Xiang, Y., Yu, S., Li, B., & Zheng, G. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2977383 · Cited by 451 · cited 1×
“Moreover, having a Single Point of Failure (SPF) in the system is not ideal since a compromised server can affect the whole network [4].”
BackgroundLyu, L., Yu, H., Zhao, J., & Yang, Q. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_1 · Cited by 444
Self-citationHardy, 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 2×
“Another example is [25], which uses an additively homomorphic architecture to defeat honest-but-curious adversaries using federated logistic regression on the encrypted vertical FL data.”
BackgroundBlockchain for 5G and beyond networks: A state of the art survey
Nguyen, D. C., Pathirana, P. N., Ding, M., & Seneviratne, A. (2020) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2020.102693 · Cited by 412
Attack of the tails: Yes, you really can backdoor federated learning
Wang, H., Sreenivasan, K., Rajput, S., Vishwakarma, H., Agarwal, S., Sohn, J.-Y., Lee, K., & Papailiopoulos, D. (2020) · arXiv · doi:10.48550/arxiv.2007.05084 · Cited by 406
Dong, J., Roth, A., & Su, W. J. (2019) · arXiv · doi:10.48550/arxiv.1905.02383 · Cited by 389
I Have a DREAM! (DiffeRentially privatE smArt Metering)
Ács, G., & Castelluccia, C. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-24178-9_9 · Cited by 388 · cited 2×
“It has been also mentioned that SMC is best to be coupled with DP to secure the communications [89], [90].”
BackgroundBiscotti: A blockchain system for private and secure federated learning
Shayan, M., Fung, C., Yoon, C. J. M., & Beschastnikh, I. (2021) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2020.3044223 · Cited by 354
On Safeguarding Privacy and Security in the Framework of Federated Learning
Ma, C., Li, J., Ding, M., Yang, H. H., Shu, F., Quek, T. Q. S., & Poor, H. V. (2020) · IEEE Network · doi:10.1109/mnet.001.1900506 · Cited by 318
Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
Caldas, S., Konečny, J., McMahan, H. B., & Talwalkar, A. (2018) · arXiv · doi:10.48550/arxiv.1812.07210 · Cited by 312 · cited 1×
“In addition, Table V specifies mechanisms that each reviewed DFL method employs.”
MethodSecure 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 1×
“Moreover, non-linear estimations in statistical models demandapproximatingpolynomialswhichmakesitimportantto find a balance between utility and privacy [101], [102].”
BackgroundVulnerabilities in federated learning
Bouacida, N., & Mohapatra, P. (2021) · IEEE Access · doi:10.1109/access.2021.3075203 · Cited by 248
A uror: defending against poisoning attacks in collaborative deep learning systems
Shen, S., Tople, S., & Saxena, P. (2016) · Proceedings of the 32nd Annual Conference on Computer Security Applications · doi:10.1145/2991079.2991125 · Cited by 228
Threats to federated learning A survey
Lyu, L., Yu, H., & Yang, Q. (2020) · arXiv · doi:10.48550/arxiv.2003.02133 · Cited by 221 · cited 1×
“On the other hand, surveys on security and privacy of centralized FL [14], [15], [16], [17], [18], [19] do not discuss the applicability of their analysis and findings to DFL.”
BackgroundSelf-citationA Taxonomy of Attacks on Federated Learning
Jere, M. S., Farnan, T., & Koushanfar, F. (2021) · IEEE Security & Privacy · doi:10.1109/msec.2020.3039941 · Cited by 217 · cited 1×
“On the other hand, surveys on security and privacy of centralized FL [14], [15], [16], [17], [18], [19] do not discuss the applicability of their analysis and findings to DFL.”
BackgroundAli, M., Karimipour, H., & Tariq, M. (2021) · Computers & Security · doi:10.1016/j.cose.2021.102355 · Cited by 177
Drones’ Edge Intelligence Over Smart Environments in B5G: Blockchain and Federated Learning Synergy
Alsamhi, S. H., Almalki, F. A., Afghah, F., Hawbani, A., Shvetsov, A. V., Lee, B., & Song, H. (2022) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2021.3132561 · Cited by 139
AI at the Edge: Blockchain-Empowered Secure Multiparty Learning With Heterogeneous Models
Wang, Q., Guo, Y., Wang, X., Ji, T., Yu, L., & Li, P. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2987843 · Cited by 70 · cited 1×
“By exploring novel cryptographic techniques, adaptive privacy mechanisms, and secure communication protocols, it is possible to address the security challenges that arise from the heterogeneity of DFL and ensure the confidentiality, integrity, and privacy of the FL process [158], [159].”
BackgroundHallaji, E., Razavi-Far, R., Saif, M., & Herrera-Viedma, E. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110384 · Cited by 41 · cited 1×
“As an example, reference [68] studies different variations of label poisoning in federated learning systems and mitigates these attacks by reformulating the problem as a label noise classification task.”
BackgroundSelf-citation
Cited by
Decentralized Federated Learning: A Survey and Perspective
Yuan, L., Wang, Z., Sun, L., Yu, P. S., & Brinton, C. G. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3407584 · Cited by 290
A Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy
Manzoor, H. U., Shabbir, A., Chen, A., Flynn, D., & Zoha, A. (2024) · Future Internet · doi:10.3390/fi16100374 · Cited by 58
Threats and Defenses in the Federated Learning Life Cycle: A Comprehensive Survey and Challenges
Li, Y., Guo, Z., Yang, N., Chen, H., Yuan, D., & Ding, W. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3563537 · Cited by 38
Metadata
- Authors
- Hallaji, E., Razavi-Far, R., Saif, M., Wang, B., & Yang, Q.
- Venue
- IEEE Transactions on Big Data
- Published
- 2024-04
- Volume
- 10
- Issue
- 2
- Pages
- 194-213
- ISSN
- 2332-7790 (ISSN-L)
- 2372-2096
- OpenAlex
- W4391462029
- Cited by
- 175
- References
- 57
- FWCI
- 26.04
- Type
- journal article
- Language
- en
- Open access
- green
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.