# Fluent: Round-efficient Secure Aggregation for Private Federated Learning

arXiv: https://arxiv.org/abs/2403.06143 · HTML: https://mlsanity.com/paper/2403.06143/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 74 references that are in the map.
- First posted on arXiv 10 Mar 2024.

## Builds on (most cited first, 26 of 26)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks](https://mlsanity.com/paper/1911.07135/) (2019)
- [When Machine Unlearning Jeopardizes Privacy](https://mlsanity.com/paper/2005.02205/) (2020)
- [Reconstructing Training Data with Informed Adversaries](https://mlsanity.com/paper/2201.04845/) (2022)
- [Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning](https://mlsanity.com/paper/1904.01067/) (2019)
- [PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments](https://mlsanity.com/paper/2104.14380/) (2021)
- [Eluding Secure Aggregation in Federated Learning via Model Inconsistency](https://mlsanity.com/paper/2111.07380/) (2021)
- [LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2007.15789/) (2020)
- [Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learning](https://mlsanity.com/paper/2106.03328/) (2021)
- [Prio: Private, Robust, and Scalable Computation of Aggregate Statistics](https://mlsanity.com/paper/1703.06255/) (2017)
- [LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulation](https://mlsanity.com/paper/2303.12233/) (2023)
- [EIFFeL: Ensuring Integrity for Federated Learning](https://mlsanity.com/paper/2112.12727/) (2021)
- [RoFL: Robustness of Secure Federated Learning](https://mlsanity.com/paper/2107.03311/) (2021)
- [Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors](https://mlsanity.com/paper/2112.06872/) (2021)
- [Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learning](https://mlsanity.com/paper/2308.09883/) (2023)
- [Lightweight Techniques for Private Heavy Hitters](https://mlsanity.com/paper/2012.14884/) (2020)
- [Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks](https://mlsanity.com/paper/2209.04030/) (2022)
- [Cross-silo Federated Learning with Record-level Personalized Differential Privacy](https://mlsanity.com/paper/2401.16251/) (2024)
- [ScionFL: Efficient and Robust Secure Quantized Aggregation](https://mlsanity.com/paper/2210.07376/) (2022)
- [DPAUC: Differentially Private AUC Computation in Federated Learning](https://mlsanity.com/paper/2208.12294/) (2022)
- [STAR: Secret Sharing for Private Threshold Aggregation Reporting](https://mlsanity.com/paper/2109.10074/) (2021)
- [Amplification by Shuffling without Shuffling](https://mlsanity.com/paper/2305.10867/) (2023)
- [Secure Linear Aggregation Using Decentralized Threshold Additive Homomorphic Encryption For Federated Learning](https://mlsanity.com/paper/2111.10753/) (2021)

## 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.