Lune

ICML2025Top-tier venue

Janus: Dual-Server Multi-Round Secure Aggregation with Verifiability for Federated Learning

Lang Pu, Jingjing Gu, Chao Lin, Xinyi Huang

Abstract

Secure Aggregation (SA) is a cornerstone of Federated Learning (FL), ensuring that user updates remain hidden from servers. The advanced Flamingo (S&P'23) has realized multi-round aggregation and improved efficiency. However, it still faces several key challenges: scalability issues with dynamic user participation, a lack of verifiability for server-side aggregation results, and vulnerability to Model Inconsistency Attacks (MIA) caused by a malicious server distributing inconsistent models. To address these issues, we propose Janus, a generic SA scheme based on dual-server architecture. Janus ensures security against up to n -2 colluding clients (where n is the total client count), which prevents privacy breaches for non-colluders. Additionally, Janus is model-independent, ensuring applicability across any FL model without specific adaptations. Furthermore, Janus introduces a new cryptographic primitive, Separable Homomorphic Commitment, which enables clients to efficiently verify the correctness of aggregation. Finally, extensive experiments show that Janus not only significantly enhances security but also reduces per-client communication and computation overhead from logarithmic to constant scale, with a tolerable impact on model performance.

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.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning cites Practical Secure Aggregation for Privacy-Preserving Machine Learning
  • Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning cites Membership Inference Attacks Against Machine Learning Models
  • Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning cites SecureML: A System for Scalable Privacy-Preserving Machine Learning
  • Practical Secure Aggregation for Privacy-Preserving Machine Learning cites Membership Inference Attacks Against Machine Learning Models
  • Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning cites Membership Inference Attacks Against Machine Learning Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMsMohamed Shaaban, Mohamed ElmahallawyACL 2026

Builds on15

  1. Membership Inference Attacks Against Machine Learning ModelsReza Shokri, Marco Stronati, Congzheng Song, Vitaly ShmatikovS&P 2017 · 5,137 citations
  2. Practical Secure Aggregation for Privacy-Preserving Machine LearningKallista A. Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone et al.CCS 2017 · 3,936 citations
  3. SecureML: A System for Scalable Privacy-Preserving Machine LearningPayman Mohassel, Yupeng ZhangS&P 2017 · 2,107 citations
  4. 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
  5. Deep Models Under the GAN: Information Leakage from Collaborative Deep LearningBriland Hitaj, Giuseppe Ateniese, Fernando Pérez-CruzCCS 2017 · 1,581 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. Aion: Robust and Efficient Multi-Round Single-Mask Secure Aggregation Against Malicious ParticipantsYizhong Liu, Zixiao Jia, Xiao Chen, Song Bian et al.USENIX Security 2025
  3. Lighthouse: Single-Server Secure Aggregation with O(1) Server-Committee Communication at ScaleSanjam Garg, Alireza Kavousi, Dimitris Kolonelos, Erkan Tairi et al.USENIX Security 2026 · 1 citation
  4. ELSA: Secure Aggregation for Federated Learning with Malicious ActorsMayank Rathee, Conghao Shen, Sameer Wagh, Raluca Ada PopaS&P 2023
  5. TACITA: Threshold Aggregation without Client InteractionVarun Madathil, Arthur Lazzaretti, Zeyu Liu, Charalampos PapamanthouCCS 2026 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines