mlsanityData to 7 Oct 2026

Fluent: Round-efficient Secure Aggregation for Private Federated Learning

arXiv 2403.06143 ↗First posted 10 Mar 2024cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) facilitates collaborative training of machine learning models among a large number of clients while safeguarding the privacy of their local datasets. However, FL remains susceptible to vulnerabilities such as privacy inference and inversion attacks. Single-server secure aggregation schemes were proposed to address these threats. Nonetheless, they encounter practical constraints due to their round and communication complexities. This work introduces Fluent, a round and communication-efficient secure aggregation scheme for private FL. Fluent has several improvements compared to state-of-the-art solutions like Bell et al. (CCS 2020) and Ma et al. (SP 2023): (1) it eliminates frequent handshakes and secret sharing operations by efficiently reusing the shares across multiple training iterations without leaking any private information; (2) it accomplishes both the consistency check and gradient unmasking in one logical step, thereby reducing another round of communication. With these innovations, Fluent achieves the fewest communication rounds (i.e., two in the collection phase) in the malicious server setting, in contrast to at least three rounds in existing schemes. This significantly minimizes the latency for geographically distributed clients; (3) Fluent also introduces Fluent-Dynamic with a participant selection algorithm and an alternative secret sharing scheme. This can facilitate dynamic client joining and enhance the system flexibility and scalability. We implemented Fluent and compared it with existing solutions. Experimental results show that Fluent improves the computational cost by at least 75% and communication overhead by at least 25% for normal clients. Fluent also reduces the communication overhead for the server at the expense of a marginal increase in computational cost.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 74 references that are in the map. First posted on arXiv 10 Mar 2024.

Builds on

26 of 74 references.

References · 26

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2021Membership Inference Attacks From First Principlescited by 839
  3. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  4. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  5. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  6. 2020When Machine Unlearning Jeopardizes Privacycited by 181
  7. 2022Reconstructing Training Data with Informed Adversariescited by 143
  8. 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 117
  9. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  10. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
  11. 2020LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacycited by 63
  12. 2021Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learningcited by 38
14 more
  1. 2017Prio: Private, Robust, and Scalable Computation of Aggregate Statisticscited by 35
  2. 2023LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulationcited by 35
  3. 2021EIFFeL: Ensuring Integrity for Federated Learningcited by 26
  4. 2021RoFL: Robustness of Secure Federated Learningcited by 23
  5. 2021Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errorscited by 23
  6. 2023Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learningcited by 16
  7. 2020Lightweight Techniques for Private Heavy Hitterscited by 13
  8. 2022Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attackscited by 12
  9. 2022ScionFL: Efficient and Robust Secure Quantized Aggregationcited by 8
  10. 2022DPAUC: Differentially Private AUC Computation in Federated Learningcited by 7
  11. 2024Cross-silo Federated Learning with Record-level Personalized Differential Privacycited by 7
  12. 2021STAR: Secret Sharing for Private Threshold Aggregation Reportingcited by 2
  13. 2023Amplification by Shuffling without Shufflingcited by 2
  14. 2021Secure Linear Aggregation Using Decentralized Threshold Additive Homomorphic Encryption For Federated Learningcited by 1

Built on by

Not cited yet.