mlsanityData to 7 Oct 2026

Fundamental Limits of Hierarchical Secure Aggregation with Cyclic User Association

arXiv 2503.04564 ↗First posted 6 Mar 2025cs.IT cs.AI cs.CRcited by 7

Not on the map. Why?

Abstract (arXiv)

Secure aggregation is motivated by federated learning (FL) where a cloud server aims to compute an aggregated model (i.e., weights of deep neural networks) of the locally-trained models of numerous clients through an iterative communication process, while adhering to data security requirements. Hierarchical secure aggregation (HSA) extends this concept to a three-layer hierarchical network, where clustered users communicate with the server through an intermediate layer of relays. In HSA, beyond conventional server security, relay security is also enforced to ensure that the relays remain oblivious to the users' inputs (an abstraction of the local models in FL). Existing studies on HSA that jointly consider communication and secret key generation efficiency typically assume that each user is associated with only one relay, limiting opportunities for coding across inter-cluster users to achieve efficient communication and key generation. In this paper, we consider HSA with a cyclic association pattern where each user is connected to B consecutive relays in a wrap-around manner. We propose an efficient aggregation scheme which includes a message design for the inputs inspired by gradient coding-a well-known technique for efficient communication in distributed computing-along with a highly non-trivial security key design.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 21 of its 52 references that are in the map. First posted on arXiv 6 Mar 2025.

Builds on

21 of 52 references.

References · 21

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  4. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  5. 2020The Future of Digital Health with Federated Learningcited by 625
  6. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  7. 2019Differentially Private Learning with Adaptive Clippingcited by 218
  8. 2018Applied Federated Learning: Improving Google Keyboard Query Suggestionscited by 202
  9. 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
  10. 2020Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learningcited by 78
  11. 2020Local Differential Privacy based Federated Learning for Internet of Thingscited by 74
  12. 2021LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learningcited by 63
9 more
  1. 2020FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learningcited by 60
  2. 2018Communication-Computation Efficient Gradient Codingcited by 26
  3. 2020Secure Aggregation with Heterogeneous Quantization in Federated Learningcited by 21
  4. 2021Information Theoretic Secure Aggregation with User Dropoutscited by 19
  5. 2022SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learningcited by 18
  6. 2022Efficient Dropout-resilient Aggregation for Privacy-preserving Machine Learningcited by 18
  7. 2022Self-Aware Personalized Federated Learningcited by 16
  8. 2022SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guaranteescited by 14
  9. 2023Private Aggregation in Hierarchical Wireless Federated Learning with Partial and Full Collusioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 3.

7 papers.

  1. 2025MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Modelscited by 7
  2. 2025Hierarchical Secure Aggregation with Heterogeneous Security Constraints and Arbitrary User Collusioncited by 2
  3. 2025Information-Theoretic Decentralized Secure Aggregation with Passive Collusion Resiliencecited by 2
  4. 2025Perfect Privacy for Discriminator-Based Byzantine-Resilient Federated Learningcited by 0
  5. 2026Coding-Enforced Resilient and Secure Aggregation for Hierarchical Federated Learningcited by 0
  6. 2026DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learningcited by 0
  7. 2026Information-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversariescited by 0