Practical Secure Aggregation for Privacy-Preserving Machine Learning
The DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index.
Abstract
We design a novel, communication-efficient, failure-robust protocol for secure aggregation of high-dimensional data. Our protocol allows a server to compute the sum of large, user-held data vectors from mobile devices in a secure manner (i.e. without learning each user's individual contribution), and can be used, for example, in a federated learning setting, to aggregate user-provided model updates for a deep neural network. We prove the security of our protocol in the honest-but-curious and active adversary settings, and show that security is maintained even if an arbitrarily chosen subset of users drop out at any time. We evaluate the efficiency of our protocol and show, by complexity analysis and a concrete implementation, that its runtime and communication overhead remain low even on large data sets and client pools. For 16-bit input values, our protocol offers $1.73 x communication expansion for 210 users and 220-dimensional vectors, and 1.98 x expansion for 214 users and 224-dimensional vectors over sending data in the clear.
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
“Although SMC guarantees that none of the parties shares anything with each other or with any third party, it can not prevent an adversary from learning some individual information”
From Federated Learning for Healthcare Informatics (2021) · cites this paper as [8]
In the citing paper
“By combining local inference with trusted aggregation, TDAI can enhance both privacy and robustness of anomaly detection pipelines [239].”
From Anomaly detection and root-cause identification in microservices: a survey (2026) · cites this paper as [239]
In the citing paper
“FL is still in its infancy and is still vulnerable to various challenges [148,149].”
From Smart Wearables for the Detection of Cardiovascular Diseases: A Systematic Literature Review (2023) · cites this paper as [148]
In the citing paper
“Therefore, many FL frameworks use secure aggregation [81], [82], [83], [84] algorithms in the aggregation process, at which point most of the poisoning attack defense methods mentioned above will be invalid.”
From Poisoning attacks in federated learning: A survey (2023) · cites this paper as [81]
In the citing paper
“Bonawitz et al. [62] introduce a secure aggregation protocol for protecting individual model updates.”
From Handling privacy-sensitive medical data with federated learning: Challenges and future directions (2023) · cites this paper as [62]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
New directions in cryptography
Diffie, W., & Hellman, M. (1976) · IEEE Transactions on Information Theory · doi:10.1109/tit.1976.1055638 · Cited by 14,713
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 · cited 1×
“maintains a private database of her text messages securely on her own mobile device, and a shared global model is trained under the coordination of a central server based upon highly processed, minimally scoped, ephemeral updates from users [20], [10].”
BackgroundSelf-citationShamir, A. (1979) · Communications of the ACM · doi:10.1145/359168.359176 · Cited by 13,756 · cited 1×
“We rely on Shamir’s t -out-of- n Secret Sharing [38], which allows a user to split a secret s into n shares, such that any t shares can be used to reconstruct s , but any set of at most t − 1 shares gives no information about s .”
Method(2016) · Cited by 11,679
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 · cited 3×
“This is particular advantageous in the local privacy setting [13], which offers provable guarantees for the protection of individual training examples [14], [15] even when the data aggregator is not assumed to be trusted [16], [17].”
BackgroundMethodSelf-citationThe 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
Dwork, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11787006_1 · Cited by 5,291 · cited 1×
“In such cases, secure aggregation composes well with differential privacy [12].”
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
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
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
Self-citation
Research works printed but not linked: 3
- Stephen Advokat. 1987. Publication Of Bork's Video Rentals Raises Privacy Issue. Chicago Tribune (1987).
- Michael Barbaro, Tom Zeller, and Saul Hansell. 2006. A face is exposed for AOL searcher no. 4417749. New York Times 9, 2008 (2006).
- Elaine Shi, HTH Chan, Eleanor Rieffel, Richard Chow, and Dawn Song. 2011. Privacy-preserving aggregation of time-series data. In Annual Network & Distributed System Security Symposium (NDSS). Internet Society.
Cited by
Items 101–200 of 1,035
Blockchain-Based Federated Learning for Securing Internet of Things: A Comprehensive Survey
Issa, W., Moustafa, N., Turnbull, B., Sohrabi, N., & Tari, Z. (2023) · ACM Computing Surveys · doi:10.1145/3560816 · Cited by 319
“For example, Bonawitz et al. [20] and Gao et al. [46] employed a secret sharing mechanism to design FL frameworks that are able to preserve the participant’s privacy.”
BackgroundTurbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning
So, J., Guler, B., & Avestimehr, A. S. (2021) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2021.3054610 · Cited by 318
“This approach, also known as secure aggregation [3], [4], does not sacrifice the convergence performance.”
BackgroundMethodInfluentialRauniyar, A., Hagos, D. H., Jha, D., Håkegård, J. E., Bagci, U., Rawat, D. B., & Vlassov, V. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3329061 · Cited by 315
“The amalgamation of decentralized data and collaborative FL approaches [75] aligns seamlessly with the decentralized nature of blockchain and can expedite the development of AI applications in healthcare.”
BackgroundFedML: A Research Library and Benchmark for Federated Machine Learning
He, C., Li, S., So, J., Zeng, X., Zhang, M., Wang, H., Wang, X., Vepakomma, P., Singh, A., Qiu, H., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13518 · Cited by 314
“Finally, we plan to provide a sample implementation of the secure aggregation algorithm [113], using the above APIs.”
BackgroundMethodVeriFL: Communication-Efficient and Fast Verifiable Aggregation for Federated Learning
Guo, X., Liu, Z., Li, J., Gao, J., Hou, B., Dong, C., & Baker, T. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3043139 · Cited by 314
Byzantine-Resilient Secure Federated Learning
So, J., Guler, B., & Avestimehr, A. S. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3041404 · Cited by 313
Blockchain-empowered Federated Learning: Challenges, Solutions, and Future Directions
Zhu, J., Cao, J., Saxena, D., Jiang, S., & Ferradi, H. (2023) · ACM Computing Surveys · doi:10.1145/3570953 · Cited by 309
“Data privacy Diferential privacy [65] [6, 35, 77] Secure multi-party computation [10]”
BackgroundMethodPrivacy-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
Multi-Objective Evolutionary Federated Learning
Zhu, H., & Jin, Y. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2919699 · Cited by 301
“[3] gives an overview of cryptographic techniques like homomorphic encryption [4] to encrypt the uploaded information before”
BackgroundThree Approaches for Personalization with Applications to Federated Learning
Mansour, Y., Mohri, M., Ro, J. H., & Suresh, A. T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.10619 · Cited by 301
Secure and Efficient Federated Learning for Smart Grid With Edge-Cloud Collaboration
Su, Z., Wang, Y., Luan, T. H., Zhang, N., Li, F., Chen, T., & Cao, H. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3095506 · Cited by 301
When the Curious Abandon Honesty: Federated Learning Is Not Private
Boenisch, F., Dziedzic, A., Schuster, R., Shamsabadi, A. S., Shumailov, I., & Papernot, N. (2023) · 2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp57164.2023.00020 · Cited by 145
“Note that [37]’s main goal is not to extract large amounts individual user data points but user updates, by circumventing the secure aggregation [6] used to protect the FL protocol.”
BackgroundFastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning
Kadhe, S., Rajaraman, N., Koyluoglu, O. O., & Ramchandran, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.11248 · Cited by 108
“FastSecAgg achieves smaller computation cost than SecAgg+ at the server and the same (orderwise) communication cost per client as SecAgg+ when L = Ω ( N ) .”
BackgroundMethodInfluentialPrivacy-Preserving Machine Learning: Methods, Challenges and Directions
Xu, R., Baracaldo, N., & Joshi, J. B. D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.04417 · Cited by 78
“Existing cryptographic approaches for data publishing for ML training fall into following two directions: (i) utilizing traditional symmetric encryption schemes such as AES in conjunction with the garbled-circuits and oblivious transfer to achieve general secure multi-party computation protocols [103, 104, 105] and (a…”
BackgroundMethodInfluentialRodríguez-Barroso, N., Jiménez-López, D., Luzón, M. V., Herrera, F., & Martínez-Cámara, E. (2023) · Information Fusion · doi:10.1016/j.inffus.2022.09.011 · Cited by 296
“[140] defined an efficient and robust SMPC protocol for the aggregation procedure and, later on, studied its parameter selection [141].”
MethodFederated Adversarial Domain Adaptation
Peng, X., Huang, Z., Zhu, Y., & Saenko, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.02054 · Cited by 128
“Federated Learning (FL) (Mohassel & Rindal, 2018; Bonawitz et al., 2017; Mohassel & Zhang, 2017) provides a privacy-preserving mechanism to leverage such decen-tralized data and computation resources to train machine learning models.”
FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
He, C., Balasubramanian, K., Ceyani, E., Yang, C., Xie, H., Sun, L., He, L., Yang, L., Yu, P. S., Rong, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.07145 · Cited by 95
PoisonGAN: Generative Poisoning Attacks Against Federated Learning in Edge Computing Systems
Zhang, J., Chen, B., Cheng, X., Binh, H. T. T., & Yu, S. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3023126 · Cited by 291
“1) A federated learning protocol usually integrates the secure aggregation method [36] to prevent the central server from leaking the participants’ local model updates, this cryptography-based solution brings significant difficulties to detect which party submits the abnormal local updates.”
MethodFederated 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
Blockchain-enabled Federated Learning: A Survey
Qu, Y., Uddin, M. P., Gan, C., Xiang, Y., Gao, L., & Yearwood, J. (2023) · ACM Computing Surveys · doi:10.1145/3524104 · Cited by 286
“The works presented in a conventional ML context for privacy preservation using the DP mechanism [12–14, 79–81], HC [15–17], and SMPC [18–20] are further adopted in the FL setup; [82–86] demonstrate additional privacy supports using DP, while [87, 88] present the mechanism for privacy preservation based on SMPC.”
MethodXONN: XNOR-based Oblivious Deep Neural Network Inference
Riazi, M. S., Samragh, M., Chen, H., Laine, K., Lauter, K., & Koushanfar, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.07342 · Cited by 152
Fusion of Federated Learning and Industrial Internet of Things: A survey
Boobalan, P., Ramu, S. P., Pham, Q.-V., Dev, K., Pandya, S., Maddikunta, P. K. R., Gadekallu, T. R., & Huynh-The, T. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109048 · Cited by 280
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings
du Terrail, J. O., Ayed, S.-S., Cyffers, E., Grimberg, F., He, C., Loeb, R., Mangold, P., Marchand, T., Marfoq, O., Mushtaq, E., et al. (2022) · neural information processing systems · doi:10.52202/068431-0384 · Cited by 286
Fast-Convergent Federated Learning
Nguyen, H. T., Sehwag, V., Hosseinalipour, S., Brinton, C. G., Chiang, M., & Vincent Poor, H. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3036952 · Cited by 277
Edge Intelligence: Empowering Intelligence to the Edge of Network
Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., Jiang, T., Crowcroft, J., & Hui, P. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3119950 · Cited by 272
Neurotoxin: Durable Backdoors in Federated LearningPreprint
Zhang, Z. J., Panda, A., Song, L., Yang, Y. L., Mahoney, M. W., Gonzalez, J. E., Ramchandran, K., & Mittal, P. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.10341 · Cited by 280
“Detection defenses are unused in FL deployments because they are incompatible with deployed Secure Aggregation (Bonawitz et al., 2017) methods that make it impossible for the server to view individual gradients for privacy reasons.”
Responsible AI Pattern Catalogue: A Collection of Best Practices for AI Governance and Engineering
Lu, Q., Zhu, L., Xu, X., Whittle, J., Zowghi, D., & Jacquet, A. (2024) · ACM Computing Surveys · doi:10.1145/3626234 · Cited by 121
“The federated learner [15, 18, 68–70, 112, 113, 117] preserves the data privacy by training models locally on the client devices and formulating a global model on a central server based on the local model updates (e.g., train the visual perception model locally in each vehicle).”
MethodDistributed Differential Privacy via Shuffling
Cheu, A., Smith, A., Ullman, J., Zeber, D., & Zhilyaev, M. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-17653-2_13 · Cited by 268
“They generally either (1) focus on simple summations and require a single “semi-honest”/“honest-but-curious” server that aggregates user answers, as in [26, 9, 6] ; or (2) allow general computations, but require a network of servers, a majority of whom are assumed to behave honestly, as in [11].”
BackgroundPrivacy-Preserving Federated Learning Framework Based on Chained Secure Multiparty Computing
Li, Y., Zhou, Y., Jolfaei, A., Yu, D., Xu, G., & Zheng, X. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3022911 · Cited by 265
“the secret-sharing mechanism [14]–[17].”
BackgroundEdge Intelligence: Architectures, Challenges, and Applications
Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., Jiang, T., Crowcroft, J., & Hui, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12172 · Cited by 120
“which makes the participant updates un-inspectable by the central server [137].”
BackgroundYang, Q., Liu, Y., Cheng, Y., Kang, Y., Chen, T., & Yu, H. (2019) · Synthesis lectures on artificial intelligence and machine learning · doi:10.2200/s00960ed2v01y201910aim043 · Cited by 261
Edge AI with Mosquitto: Secure, QoS-Aware Federated Anomaly Detection
Pasupuleti, M. K. (2023) · International Journal of Academic and Industrial Research Innovations(IJAIRI) · doi:10.62311/nesx/rp-30623-195-210 · Cited by 264
Privacy-Preserving Aggregation in Federated Learning: A Survey
Liu, Z., Guo, J., Yang, W., Fan, J., Lam, K., & Zhao, J. (2022) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2022.3190835 · Cited by 262
Analyzing User-Level Privacy Attack Against Federated Learning
Song, M., Wang, Z., Zhang, Z., Song, Y., Wang, Q., Ren, J., & Qi, H. (2020) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3000372 · Cited by 257
“Reference [19] discussed the weakness of encryption-based protocol that it cannot guarantee the correctness of federated learning if there are malicious clients.”
BackgroundMethodInfluentialProfit Allocation for Federated Learning
Song, T., Tong, Y., & Wei, S. (2019) · 2019 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata47090.2019.9006327 · Cited by 253
“Following [2], researchers propose other optional privacy preserving techniques such as Secure Multi-party Computation [9]–[11], Homomorphic Encryption [3], [12], [13] and Differential Privacy [14]–[17].”
MethodMachine Learning for Microcontroller-Class Hardware: A Review
Saha, S. S., Sandha, S. S., & Srivastava, M. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3210773 · Cited by 253
“Federated learning [27], secure aggregation [28], and homomorphic encryption [29] allow privacy-preserving and secure inference, but suffer from expensive network and compute requirement.”
BackgroundPrivacy-Preserving Federated Learning in Fog Computing
Zhou, C., Fu, A., Yu, S., Yang, W., Wang, H., & Zhang, Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2987958 · Cited by 252
“Some researches [20], [23], [32] also fail in preventing the collusion Motivated by the above issues, we introduce fog computing into our scheme and design the “IoT Devices–Fog Nodes–Cloud” architecture, which comprises the advantages of both centralized and distributed training modes.”
BackgroundMethodAddressing Class Imbalance in Federated Learning
Wang, L., Xu, S., Wang, X., & Zhu, Q. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i11.17219 · Cited by 251
“The privacy protection in FL training is guaranteed by secure aggregation protocols (Bonawitz et al. 2017) and differential privacy techniques (Geyer, Klein, and Nabi 2017; Niu et al.”
MethodFederated learning: Overview, strategies, applications, tools and future directions
Yurdem, B., Kuzlu, M., Gullu, M. K., Catak, F. O., & Tabassum, M. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e38137 · Cited by 251
Duan, M., Liu, D., Chen, X., Tan, Y., Ren, J., Qiao, L., & Liang, L. (2019) · 2019 IEEE 37th International Conference on Computer Design (ICCD) · doi:10.1109/iccd46524.2019.00038 · Cited by 250
“ducing communication overhead [3], [10]–[12] and protecting privacy [13]–[16], but only a few studies have noticed the problem of accuracy degradation due to imbalance [4], [17].”
BackgroundTowards Fair and Privacy-Preserving Federated Deep Models
Lyu, L., Yu, J., Nandakumar, K., Li, Y., Ma, X., Jin, J., Yu, H., & Ng, K. S. (2020) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2020.2996273 · Cited by 250
“[24] proposed a practical secure aggregation protocol, which is proven to be secure under the honest-but-curious and active adversary settings, even”
BackgroundDuan, M., Liu, D., Chen, X., Tan, Y., Ren, J., Qiao, L., & Liang, L. (2019) · arXiv · doi:10.48550/arxiv.1907.01132 · Cited by 250
“ducing communication overhead [3], [10]–[12] and protecting privacy [13]–[16], but only a few studies have noticed the problem of accuracy degradation due to imbalance [4], [17].”
BackgroundVulnerabilities in federated learning
Bouacida, N., & Mohapatra, P. (2021) · IEEE Access · doi:10.1109/access.2021.3075203 · Cited by 248
When Federated Learning Meets Privacy-Preserving Computation
Chen, J., Yan, H., Liu, Z., Zhang, M., Xiong, H., & Yu, S. (2024) · ACM Computing Surveys · doi:10.1145/3679013 · Cited by 247
“The philosophy of this protocol is different from protocols [76, 87, 125] based on SMC, HE, DP.”
InfluentialYin, F., Lin, Z., Kong, Q., Xu, Y., Li, D., Theodoridis, S., & Cui, S. R. (2020) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2020.3036276 · Cited by 247
“tion [77]. By exploiting a secure aggregation protocol and a secretsharing scheme, the privacy of each user-provided model can be guaranteed under an honest-but-curious and active adversarial setting [78], which supports an arbitrary subset of user dropouts. Other than the above schemes, to verify the correctness of t…”
BackgroundFederated Learning for Open Banking
Long, G., Tan, Y., Jiang, J., & Zhang, C. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_17 · Cited by 244
“Therefore, differential privacy, secure aggregation [4], and homomorphic encryption are widely used methods for data protection in the federated learning framework.”
MethodSAFELearn: Secure Aggregation for private FEderated Learning
Fereidooni, H., Marchal, S., Miettinen, M., Mirhoseini, A., Mollering, H., Nguyen, T. D., Rieger, P., Sadeghi, A.-R., Schneider, T., Yalame, H., et al. (2021) · 2021 IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw53761.2021.00017 · Cited by 244
“Turbo-Aggregate [22] reduces the communication and computation overhead of secure aggregation over [14] (cf.”
BackgroundMethodInfluentialA Federated Learning Approach to Anomaly Detection in Smart Buildings
Sater, R. A., & Hamza, A. B. (2021) · ACM Transactions on Internet of Things · doi:10.1145/3467981 · Cited by 243
“as mobile phones, wearable devices and smart sensors without uploading their privacy-sensitive data to a central server or service provider [9]–[17], while reducing communication cost [18].”
Membership Inference Attacks and Defenses in Federated Learning: A Survey
Bai, L., Hu, H., Ye, Q., Li, H., Wang, L., & Xu, J. (2024) · ACM Computing Surveys · doi:10.1145/3704633 · Cited by 247
“Following this study, SecAgg [127] is proposed to protect FL from an honest but curious server.”
Protection Against Reconstruction and Its Applications in Private Federated Learning
Bhowmick, A., Duchi, J. C., Freudiger, J., Kapoor, G., & Rogers, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.00984 · Cited by 240
“Other approaches to protecting individual updates is to use secure multiparty computation (SMC), sometimes in conjunction with differential privacy protections; see, for example, Bonawitz et al. [17].”
BackgroundFedGroup: Efficient Federated Learning via Decomposed Similarity-Based Clustering
Duan, M., Liu, D., Ji, X., Liu, R. P., Liang, L., Chen, X., & Tan, Y. (2021) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom52081.2021.00042 · Cited by 241
“Note that, unlike the previous FedAvg-based frameworks [2], [12], [20], [30], [31], the optimization gradients in the server is not broadcast to all clients or groups, we only maintain this gradients for the cold start of newcomers.”
Chellapandi, V. P., Yuan, L., Brinton, C. G., Żak, S. H., & Wang, Z. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3332675 · Cited by 236
“Cloud servers perform a secure aggregation of the received gradients/weights and update the global model parameters that are transmitted back to clients/edge devices [34].”
Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
Tramèr, F., & Boneh, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.03287 · Cited by 233
“, hiding user data from the server) can be achieved via cryptographic means [2].”
BackgroundA Survey on Federated Unlearning: Challenges, Methods, and Future Directions
Liu, Z., Jiang, Y., Shen, J., Peng, M., Lam, K., Yuan, X., & Liu, X. (2024) · ACM Computing Surveys · doi:10.1145/3679014 · Cited by 236
“Thus, privacy-preserving aggregation protocols [4, 5, 40, 85] are essential to maintain the security and privacy of the model aggregation process in Step iii of FL. Additionally, FL is susceptible to poisoning attacks [90] (see Section 3.4 for more details).”
BackgroundInfluentialArtificial Intelligence in Medical Sensors for Clinical Decisions
Haick, H., & Tang, N. (2021) · ACS Nano · doi:10.1021/acsnano.1c00085 · Cited by 231
Federated Learning for Emoji Prediction in a Mobile Keyboard
Ramaswamy, S., Mathews, R., Rao, K., & Beaufays, F. (2019) · arXiv · doi:10.48550/arxiv.1906.04329 · Cited by 231
“FL can be combined with other privacy-preserving techniques like secure multi-party computation (Bonawitz et al., 2017) and differential privacy (McMahan et al., 2018; Agarwal et al., 2018; Abadi et al., 2016).”
BackgroundFederated Learning of a Mixture of Global and Local Models
Hanzely, F., & Richtárik, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.05516 · Cited by 230
A Survey on Trustworthy Recommender Systems
Ge, Y., Liu, S., Fu, Z., Tan, J., Li, Z., Xu, S., Li, Y., Xian, Y., & Zhang, Y. (2024) · ACM Transactions on Recommender Systems · doi:10.1145/3652891 · Cited by 233
“In general, the encryption techniques are often used as fundamental building blocks for multi-party and communication-rich frameworks such as federated learning and secure multi-party computation [32].”
MethodPreserving Data Privacy via Federated Learning: Challenges and Solutions
Li, Z., Sharma, V., & P. Mohanty, S. (2020) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2019.2959108 · Cited by 226
“Solutions : Bonawitz et al. [6] discussed the problem of computing a multiparty sum in federated learning by leveraging the spirit of secure aggregation protocol.”
MethodInfluentialPrivacy-first health research with federated learning
Sadilek, A., Liu, L., Nguyen, D., Kamruzzaman, M., Serghiou, S., Rader, B., Ingerman, A., Mellem, S., Kairouz, P., Nsoesie, E. O., et al. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00489-2 · Cited by 226
“Additionally, the issue of model data memorization may manifest itself in the process of federated learning 24 , just as it does with traditional, centralized machine learning 25,26 .”
BackgroundPPFL: privacy-preserving federated learning with trusted execution environments
Mo, F., Haddadi, H., Katevas, K., Marin, E., Perino, D., & Kourtellis, N. (2021) · Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3458864.3466628 · Cited by 226
“, [8]), or (iii) differential privacy (e.”
A Fairness-aware Incentive Scheme for Federated Learning
Yu, H., Liu, Z., Liu, Y., Chen, T., Cong, M., Weng, X., Niyato, D., & Yang, Q. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375840 · Cited by 226
“Under federated learning, data owners employ privacy protection techniques such as homomorphic encryption [19], secret sharing [5] and differential privacy [20] to contribute model parameters trained on their own datasets to a federation .”
BackgroundPrivacy-Preserving Federated Learning Using Homomorphic Encryption
Park, J., & Lim, H. (2022) · Applied Sciences · doi:10.3390/app12020734 · Cited by 223
“The scheme proposed in [14] can prevent leakage of local model parameters due to the noise contained in the local parameter but can be vulnerable to insider attacks because participants must actively cooperate.”
BackgroundMethodInfluentialThreats to federated learning A survey
Lyu, L., Yu, H., & Yang, Q. (2020) · arXiv · doi:10.48550/arxiv.2003.02133 · Cited by 221
“FL enables a multitude of participants to construct a joint ML model without exposing their private training data [ McMahan et al. , 2016b; Bonawitz et al. , 2017 ] .”
BackgroundCommunication-Efficient Federated Learning With Compensated Overlap-FedAvg
Zhou, Y., Ye, Q., & Lv, J. (2022) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2021.3090331 · Cited by 221
Optimal Client Sampling for Federated Learning
Chen, W., Horváth, S., & Richtárik, P. (2022) · Transactions on machine learning research · doi:10.17863/cam.89518 · Cited by 222
Moshawrab, M., Adda, M., Bouzouane, A., Ibrahim, H., & Raad, A. (2023) · Electronics · doi:10.3390/electronics12102287 · Cited by 221
“In the same year, the authors of [50] developed a novel communication-efficient, failure-robust protocol for secure aggregation of multiple and high-dimensional data.”
BackgroundMethodInfluentialVAFL: a Method of Vertical Asynchronous Federated LearningPreprint
Chen, T., Jin, X. P., Sun, Y., & Yin, W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.06081 · Cited by 216
“In the context of learning from multiple clients, it has been studied in [4; 12].”
BackgroundA Survey on Large-Scale Machine Learning
Wang, M., Fu, W., He, X., Hao, S., & Wu, X. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.3015777 · Cited by 219
“Recently, federate learning provides an alternative by bringing codes to edge devices and updating the global model with secure aggregation [30], [31].”
BackgroundCharacterizing Impacts of Heterogeneity in Federated Learning upon Large-Scale Smartphone Data
Yang, C., Wang, Q., Xu, M., Chen, Z., Bian, K., Liu, Y., & Liu, X. (2021) · Proceedings of the Web Conference 2021 · doi:10.1145/3442381.3449851 · Cited by 135
“Besides FedAvg, various aggregation algorithms are proposed to improve efficiency [28, 37, 38], ensure fairness [29], preserve privacy [6, 38], etc.”
MethodFMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MEC
Zeng, R., Zhang, S., Wang, J., & Chu, X. (2020) · 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs47774.2020.00094 · Cited by 213
“The security and privacy issue of federated learning is another popular topic [17], [18].”
BackgroundPoisoning attacks in federated learning: A survey
Xia, G., Chen, J., Yu, C., & Ma, J. (2023) · IEEE Access · doi:10.1109/access.2023.3238823 · Cited by 212
BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning
Roy, A. G., Siddiqui, S., Pölsterl, S., Navab, N., & Wachinger, C. (2019) · arXiv · doi:10.48550/arxiv.1905.06731 · Cited by 212
“Other works build on top of FL by improving communication efficiency [5], improving system scalability [1] and improving encryption for better privacy [2].”
BackgroundFeature Inference Attack on Model Predictions in Vertical Federated Learning
Luo, X., Wu, Y., Xiao, X., & Ooi, B. C. (2021) · 2021 IEEE 37th International Conference on Data Engineering (ICDE) · doi:10.1109/icde51399.2021.00023 · Cited by 212
“Federated learning (FL) [3, 4, 5, 6, 7] is an emerging paradigm for data collaboration that enables multiple data owners (i.”
BackgroundMethodA review of privacy-preserving techniques for deep learning
Boulemtafes, A., Derhab, A., & Challal, Y. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.11.041 · Cited by 211
“• Low overhead of runtime and communication, and tolerance to a large number of failing devices are among the concerns to be considered for the support of mobile applications [29].”
BackgroundMethodInfluentialFedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System
Jin, W., Yao, Y., Han, S., Gu, J., Joe-Wong, C., Ravi, S., Avestimehr, S., & He, C. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.10837 · Cited by 38
“…to these solutions providing privacy protection in FL, HE is non-interactive and dropout-resilient (vs. general secure aggregation protocols (Bonawitz et al., 2017; So et al., 2022)) and it introduces negligible model performance degradation (vs. noise-based differential privacy solutions…”
BackgroundApplications of federated learning in smart cities: recent advances, taxonomy, and open challenges
Zheng, Z., Zhou, Y., Sun, Y., Wang, Z., Liu, B., & Li, K. (2022) · Connection Science · doi:10.1080/09540091.2021.1936455 · Cited by 206
“In this case, multiparty data can be used in the FL framework because it solves the privacy problem of ML. Recent research improvements in FL have mainly focussed on statistical challenges (Smith, Chi-ang, et al., 2017) and security issues (Bonawitz et al., 2017).”
MethodBaFFLe: Backdoor Detection via Feedback-based Federated Learning
Andreina, S., Marson, G. A., Mollering, H., & Karame, G. (2021) · 2021 IEEE 41st International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs51616.2021.00086 · Cited by 205
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Hitaj, B., Ateniese, G., & Pérez‐Cruz, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.07464 · Cited by 205
“directly without transferring sensitive data to the company’s data centers [8, 49].”
BackgroundMethodFairness-aware Agnostic Federated Learning
Du, W., Xu, D., Wu, X., & Tong, H. (2021) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9781611976700.21 · Cited by 205
Neural Network Inversion in Adversarial Setting via Background Knowledge Alignment
Yang, Z., Zhang, J., Chang, E.-C., & Liang, Z. (2019) · Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3319535.3354261 · Cited by 203
“Secure & Privacy-Preserving ML In the wake of security and privacy threats posed to ML techniques, much research has been devoted to provisioning secure and privacy-preserving training of ML models [1, 11, 56, 61, 64] The threat models assumed by these techniques are to protect privacy of users’ data contributed to th…”
BackgroundFedPrompt: Communication-Efficient and Privacy-Preserving Prompt Tuning in Federated Learning
Zhao, H., Du, W., Li, F., Li, P., & Liu, G. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095356 · Cited by 208
“Consequently, several methods are proposed to protect privacy, including differential privacy (DP) [28]– [30] and secure multi-party computation (MPC) [31], [32].”
BackgroundDeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection
Rieger, P., Nguyen, T. D., Miettinen, M., & Sadeghi, A.-R. (2022) · Proceedings 2022 Network and Distributed System Security Symposium · doi:10.14722/ndss.2022.23156 · Cited by 202
“proposed preventing the aggregation server from accessing the individual model updates [5], [9].”
MethodLo, S. K., Lu, Q., Wang, C., Paik, H.-Y., & Zhu, L. (2022) · ACM Computing Surveys · doi:10.1145/3450288 · Cited by 202
“Similarly, the trained local models are also collected from either all the participating client devices [167, 168, 198] or only from selected client devices [19, 111].”
BackgroundMethodInfluentialFederated Neural Collaborative Filtering
Perifanis, V., & Efraimidis, P. S. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108441 · Cited by 201
“(4) Each participant perform a calculation to the generated weights according to MF-SecAvg, which is an extension of the SecAvg [17] protocol to handle the item profile updates.”
BackgroundMethodInfluentialMD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
Hardy, C., Le Merrer, E., & Sericola, B. (2019) · 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps.2019.00095 · Cited by 201
Recent advances on federated learning: A systematic survey
Liu, B., Lv, N., Guo, Y., & Li, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128019 · Cited by 200
FedBERT : When Federated Learning Meets Pre-training
Tian, Y., Wan, Y., Lyu, L., Yao, D., Jin, H., & Sun, L. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3510033 · Cited by 201
“FL enables a multitude of participants to construct a joint ML model without sharing their private training data [6, 36, 37, 41].”
BackgroundA systematic review of federated learning: Challenges, aggregation methods, and development tools
Guendouzi, S. B., Ouchani, S., Assaad, H. E., & Zaher, M. E. (2023) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2023.103714 · Cited by 199
An overview of implementing security and privacy in federated learning
Hu, K., Gong, S., Zhang, Q., Seng, C., Xia, M., & Jiang, S. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10846-8 · Cited by 200
Auditing Data Provenance in Text-Generation Models
Song, C., & Shmatikov, V. (2018) · arXiv · doi:10.48550/arxiv.1811.00513 · Cited by 199
On Deploying Secure Computing: Private Intersection-Sum-with-Cardinality
Ion, M., Kreuter, B., Nergiz, A. E., Patel, S., Saxena, S., Seth, K., Raykova, M., Shanahan, D., & Yung, M. M. (2020) · IEEE European Symposium on Security and Privacy · doi:10.1109/eurosp48549.2020.00031 · Cited by 198
“Google also reports using a secure computation protocol to aggregate locally trained machine learning models from mobile devices [7].”
MethodSelf-citationOpen-Source Federated Learning Frameworks for IoT: A Comparative Review and Analysis
Kholod, I., Yanaki, E., Fomichev, D., Shalugin, E., Novikova, E., Filippov, E., & Nordlund, M. (2020) · Sensors · doi:10.3390/s21010167 · Cited by 156
“However, in contrast to the ABY3 and SecureML protocols, the data owners participate in the training process by performing the training process locally and sending encrypted model weights to the aggregator, which implements the aggregation of the network gradients [28].”
MethodFairFed: Enabling Group Fairness in Federated Learning
Ezzeldin, Y. H., Yan, S., He, C., Ferrara, E., & Avestimehr, A. S. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i6.25911 · Cited by 197
Poisoning Attack in Federated Learning using Generative Adversarial Nets
Zhang, J., Chen, J., Wu, D., Chen, B., & Yu, S. (2019) · 2019 18th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/13th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE) · doi:10.1109/trustcom/bigdatase.2019.00057 · Cited by 197
“We notice that it is possible to construct the poisoning attack in federated learning for the following reasons [6]: 1) there are plenty of participants in federated learning system, it is most likely contains one or more malicious users; 2) since the participants’ local data and training process are invisible to the…”
BackgroundDifferentially Private Learning Needs Better Features (or Much More Data)
Tramèr, F., & Boneh, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.11660 · Cited by 77
“Cryptography can split the trust in a central party across users (Jayaraman et al., 2018; Bonawitz et al., 2017).”
BackgroundMethodInverting Gradients -- How easy is it to break privacy in federated learning?
Geiping, J., Bauermeister, H., Dröge, H., & Moeller, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.14053 · Cited by 195
“s crucial, e.g. for hospital data [16] or text predictions on mobile devices [3]. Ideally, any such approach is combined with provable guarantees of dierential privacy [10,25] and secure aggregation [4], however it is also generally understood that \Privacy is enhanced by the ephemeral and focused nature of the [Feder…”
BackgroundFederated unsupervised representation learning
Zhang, F., Kuang, K., Chen, L., You, Z., Shen, T., Xiao, J., Zhang⋆, Y., Wu, C., Wu, F. Q., Zhuang, Y., et al. (2023) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2200268 · Cited by 193
“To further protect data privacy of clients, cryptography technologies are applied to federated learning (Bonawitz et al. 2017).”
RoFL: Robustness of Secure Federated Learning
Lycklama, H., Burkhalter, L., Viand, A., Küchler, N., & Hithnawi, A. (2023) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp46215.2023.10179400 · Cited by 227
“Technically, in [13], ShareKeys is used to derive seeds which are”
BackgroundMethodInfluentialFederated learning: Applications, challenges and future directions
Bharati, S., Mondal, M. R. H., Podder, P., & Prasath, V. B. S. (2022) · International Journal of Hybrid Intelligent Systems · doi:10.3233/his-220006 · Cited by 198
“Their federated-learning approach is further supported by a safe aggregation technique that protects the aggregated user updates in privacy [12].”
BackgroundInfluential
Metadata
- Authors
- Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K.
- Affiliations
- Google (United States) (US)
- Cornell Tech (US)
- Venue
- Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security
- Publisher
- ACM
- Published
- 2017-10-30
- Volume
- 2017
- Pages
- 1175-1191
- ISSN
- 1543-7221 (ISSN-L)
- OpenAlex
- W2767079719
- Cited by
- 3,956
- References
- 55
- Citations by year
- 2026: 701 · 2025: 712 · 2024: 643 · 2023: 564 · 2022: 400 · 2021: 436 · 2020: 299 · 2019: 152 · 2018: 42 · 2017: 7
- FWCI
- 62.37
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGSAC Conference on Computer and Communications Security (CCS) (publishedVersion)
- IACR Cryptology ePrint Archive (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Keywords
- secure aggregation, privacy-preserving machine learning, federated learning, high-dimensional data, communication efficiency, user dropout, honest-but-curious adversary, active adversaries, secure multi-party computation
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.