Information-Theoretic Decentralized Secure Aggregation with Passive Collusion Resilience
Not on the map. Why?
Abstract (arXiv)
In decentralized federated learning (FL), multiple clients collaboratively learn a shared machine learning (ML) model by leveraging their privately held datasets distributed across the network, through interactive exchange of the intermediate model updates. To ensure data security, cryptographic techniques are commonly employed to protect model updates during aggregation. Despite growing interest in secure aggregation, existing works predominantly focus on protocol design and computational guarantees, with limited understanding of the fundamental information-theoretic limits of such systems. Moreover, optimal bounds on communication and key usage remain unknown in decentralized settings, where no central aggregator is available. Motivated by these gaps, we study the problem of decentralized secure aggregation (DSA) from an information-theoretic perspective. Specifically, we consider a network of K fully-connected users, each holding a private input -- an abstraction of local training data -- who aim to securely compute the sum of all inputs. The security constraint requires that no user learns anything beyond the input sum, even when colluding with up to T other users. We characterize the optimal rate region, which specifies the minimum achievable communication and secret key rates for DSA. In particular, we show that to securely compute one symbol of the desired input sum, each user must (i) transmit at least one symbol to others, (ii) hold at least one symbol of secret key, and (iii) all users must collectively hold no fewer than K - 1 independent key symbols. Our results establish the fundamental performance limits of DSA, providing insights for the design of provably secure and communication-efficient protocols in decentralized learning.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 25 of its 54 references that are in the map. First posted on arXiv 1 Aug 2025.
Builds on
25 of 54 references.
References · 25
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
- 2019On the Convergence of Adam and Beyondcited by 834
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
- 2018Applied Federated Learning: Improving Google Keyboard Query Suggestionscited by 202
- 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
- 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 137
- 2020Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learningcited by 78
13 more
- 2020Local Differential Privacy based Federated Learning for Internet of Thingscited by 74
- 2021LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learningcited by 63
- 2021Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systemscited by 45
- 2018COLA: Decentralized Linear Learningcited by 30
- 2021Information Theoretic Secure Aggregation with User Dropoutscited by 19
- 2022SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learningcited by 18
- 2022Efficient Dropout-resilient Aggregation for Privacy-preserving Machine Learningcited by 18
- 2022SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guaranteescited by 14
- 2016A Fundamental Tradeoff between Computation and Communication in Distributed Computingcited by 11
- 2020Privacy-Preserving Distributed Processing: Metrics, Bounds, and Algorithmscited by 8
- 2025Fundamental Limits of Hierarchical Secure Aggregation with Cyclic User Associationcited by 7
- 2023Private Aggregation in Hierarchical Wireless Federated Learning with Partial and Full Collusioncited by 5
- 2025Hierarchical Secure Aggregation with Heterogeneous Security Constraints and Arbitrary User Collusioncited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.