This paper investigates the fundamental limits of information-theoretic decentralized secure aggregation (DSA) with user dropouts. We consider a fully decentralized network where $K$ users communicate over broadcast channels without a trusted aggregation server. Each user holds a private input and aims to recover the sum of the surviving users' inputs (users may drop) while ensuring that no additional information about individual inputs is revealed to that user, even if it can collude with other users. A two-round communication protocol is considered, where we assume at least $U$ users survive and each user can collude with at most $T$ other users. For this setting, the optimal communication rate region is fully characterized: we show that DSA is infeasible if $U\le T+1$; otherwise, the optimal rate region is given by $R_1\geq 1$ and $R_2\geq \frac{1}{U-T-1}$, where $R_1$ and $R_2$ denote the first- and second-round communication rates, respectively. The proposed aggregation scheme is based on correlated secret keys constructed from $(T+1)$-private maximum distance separable (MDS) matrices, which simultaneously provide robustness against user dropouts and security against collusion. We also derive tight converse bounds that establish the optimality of the proposed scheme. Our result shows that the optimal second-round communication rate depends only on the effective redundancy level $U-T-1$ regardless the total number of users.
Information-Theoretic Secure Aggregation in Decentralized Networks
Technical University of Berlin(柏林工业大学);Guangxi University(广西大学);Huazhong University of Science and Technology(华中科技大学);the University of New South Wales(新南威尔士大学)
SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guarantees
Sharif University of Technology(谢里夫理工大学);Technische Universität Berlin(柏林工业大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学)
The Capacity of Collusion-Resilient Decentralized Secure Aggregation with Groupwise Keys
Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University(广西大学多媒体通信与网络技术重点实验室);Department of Electrical Engineering and Computer Science, Technical University of Berlin(柏林工业大学电气与计算机科学系);College of Electronic and Information Engineering, Southwest University(西南大学电子信息工程学院);School of Cyber Science and Engineering, Nanjing University of Science and Technology(南京理工大学网络空间安全学院)
Information-Theoretic Secure Aggregation over Regular Graphs
Technical University of Berlin(柏林工业大学);Guangxi University(广西大学);Huazhong University of Science and Technology(华中科技大学);University of North Texas(北德克萨斯大学);University of Florida(佛罗里达大学)
Information-Theoretic Decentralized Secure Aggregation with Passive Collusion Resilience
Department of Electrical Engineering and Computer Science, Technical University of Berlin(技术大学柏林电气工程与计算机科学系);Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University(广西多媒体通信与网络技术重点实验室,广西大学);School of Electronic Information and Communications, Huazhong University of Science and Technology(华中科技大学电子信息与通信学院);School of Electrical Engineering and Telecommunications, University of New South Wales(新南威尔士大学电子工程与电信学院)
Secure Distributed/Federated Learning: Prediction-Privacy Trade-Off for Multi-Agent System
University of Southern California(南加州大学)
分散学习是一种有效的新兴范式,用于提高多个有界计算代理的计算能力。在大数据时代,在分布式和联邦学习(DL和FL)框架内执行推理,中央服务器需要处理大量数据,同时依赖各种代理执行多个分布式训练任务。考虑到分布式计算的拓扑结构,隐私已经成为一个首要的问题。此外,假设代理的信息处理能力有限,需要一个复杂的\textit{privacy-preserving decentralization}来确保有效的计算。为此,我们研究的\textit{privacy-aware server to multi-agent assignment}问题受到信息处理的限制与每个代理,同时保持隐私和确保学习信息的消息,通过分布式私人联邦学习(DPFL)的方法收到代理全球终端。为了找到一个分散的计划,两个代理系统,我们制定了一个优化问题,平衡隐私和准确性,考虑到与每个代理相关联的压缩约束的质量。我们提出了一个迭代收敛算法交替自洽方程。我们还对所提出的解决方案进行了数值评估,以显示隐私预测的权衡,并证明了新方法在确保DL和FL隐私方面的有效性。
LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning
University of Southern California(南加利福尼亚大学);Mediatek Inc.(联发科技股份有限公司);The Hong Kong University of Science and Technology(香港科技大学);Princeton University(普林斯顿大学);University of California at Riverside(加州大学河滨分校)