Lune

USENIX Security2025Top-tier venue

Aion: Robust and Efficient Multi-Round Single-Mask Secure Aggregation Against Malicious Participants

Yizhong Liu, Zixiao Jia, Xiao Chen, Song Bian, Runhua Xu, Dawei Li, Yuan Lu

Abstract

Federated learning enables multiple clients to collaboratively train a model without sharing their data. Secure aggregation (SA) allows for the computation of aggregated models while protecting the private models of clients from disclosure, making it highly promising in large-scale real-world applications. Masking-based SA stands out due to its higher efficiency and accuracy. However, existing masking-based SA methods face issues such as high overhead, loss of correctness under poisoning attacks, and inability to tolerate malicious participants. In this paper, we propose Aion, a robust and efficient multiround single-mask SA tolerating malicious participants. We introduce an aggregatable SA pattern in which each client only adds a single mask and performs only one secret sharing operation, while each aggregator only reconstructs a total secret or mask. Compared to Flamingo (S&P'23), this reduces the secret sharing times from 𝑟𝑞 to 𝑞 (𝑟 for training round number and 𝑞 for client number per round) and lowers 𝑛 aggregators' mask reconstruction overhead from 𝑂 (𝑛 2 𝑞) to 𝑂 (𝑛). Furthermore, we design a lightweight evolving input validation mechanism that efficiently filters out malicious client models by dynamically updating the mask range and overall bound, thereby improving model accuracy. Besides, we present robustness enhancements that tolerate malicious clients and aggregators. These constructions support aggregator share verification and asynchronous client model utilization. Finally, experiments demonstrate that Aion outperforms Flamingo by a factor of 563.64 in speed while achieving a 97.98% reduction in message overhead with 4096 clients and 8 aggregators, effectively defending against poisoning attacks with low overhead.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • BatchCrypt: Efficient Homomorphic Encryption for Cross-Silo Federated Learning cites Practical Secure Aggregation for Privacy-Preserving Machine Learning
  • Evaluating Gradient Inversion Attacks and Defenses in Federated Learning cites Inverting Gradients - How easy is it to break privacy in federated learning?
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on20

  1. Practical Secure Aggregation for Privacy-Preserving Machine LearningKallista A. Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone et al.CCS 2017 · 3,936 citations
  2. Inverting Gradients - How easy is it to break privacy in federated learning?Jonas Geiping, Hartmut Bauermeister, Hannah Dröge, Michael MoellerNeurIPS 2020 · 1,822 citations
  3. Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated LearningMilad Nasr, Reza Shokri, Amir HoumansadrS&P 2019 · 1,778 citations
  4. BatchCrypt: Efficient Homomorphic Encryption for Cross-Silo Federated LearningChengliang Zhang, Suyi Li, Junzhe Xia, Wei Wang et al.USENIX ATC 2020 · 967 citations
  5. Evaluating Gradient Inversion Attacks and Defenses in Federated LearningYangsibo Huang, Samyak Gupta, Zhao Song, Kai Li et al.NeurIPS 2021 · 419 citations

Related papers

  1. Input Integrity and Authentic Results: Towards Trustworthy Aggregation in Federated LearningZhangshuang Guan, Yulin Zhao, Zhiguo Wan, Wei WangINFOCOM 2025 · 1 citation
  2. Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated LearningYiping Ma, Jess Woods, Sebastian Angel, Antigoni Polychroniadou et al.S&P 2023
  3. Janus: Dual-Server Multi-Round Secure Aggregation with Verifiability for Federated LearningLang Pu, Jingjing Gu, Chao Lin, Xinyi HuangICML 2025
  4. ELSA: Secure Aggregation for Federated Learning with Malicious ActorsMayank Rathee, Conghao Shen, Sameer Wagh, Raluca Ada PopaS&P 2023
  5. RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure AggregationPeihua Mai, Ran Yan, Yan PangNeurIPS 2024 · 51 citations
Dusk over the sea between two cliffs drawn in fine vertical lines