9 papers
The Capacity of Information-Theoretic Secure Aggregation in Federated Learning
Lanxin Yi, Jinbao Zhu, Kai Wan +1
Secure aggregation allows a server to aggregate users' local updates while preserving update privacy. Existing information-theoretic problems typically assume that correlated rando…
On Secure Gradient Coding with Uncoded Groupwise Keys
Xudong You, Kai Wan, Xiang Zhang +3
This paper considers a new secure gradient coding problem with uncoded groupwise keys, formalized as a (K, N, N_r, M, S) secure gradient coding model, where a user aims to compute…
Hierarchical Secure Distributed Linearly Separable Computation with Arbitrary Heterogeneous Data Assignment
Chenyi Sun, Ziting Zhang, Kai Wan +1
This paper studies secure distributed linearly separable computation over a three-layer hierarchical network, where clustered users communicate with a central server through relays…
Information-Theoretic Secure Aggregation over Regular Graphs
Xiang Zhang, Zhou Li, Han Yu +4
Large-scale decentralized learning frameworks such as federated learning (FL), require both communication efficiency and strong data security, motivating the study of secure aggreg…
Optimal Rate Region for Multi-server Secure Aggregation with User Collusion
Zhou Li, Xiang Zhang, Kai Wan +3
Secure aggregation is a fundamental primitive in privacy-preserving distributed learning systems, where an aggregator aims to compute the sum of users' inputs without revealing ind…
Information-Theoretic Secure Aggregation in Decentralized Networks
Xiang Zhang, Zhou Li, Shuangyang Li +3
Motivated by the increasing demand for data security in decentralized federated learning (FL) and stochastic optimization, we formulate and investigate the problem of information-t…
On hierarchical secure aggregation against relay and user collusion
Min Xu, Xuejiao Han, Kai Wan +1
Secure aggregation (SA) is fundamental to privacy preservation in federated learning (FL), enabling model aggregation while preventing disclosure of individual user updates. This p…
Encoded Jamming Secure Communication for RIS-Assisted Systems
Hao Yang, Hao Xu, Kai Wan +2
This paper investigates a cooperative jamming (CJ)-aided secure wireless communication system. Conventional CJ schemes transmit Gaussian noise (GN) to improve security, which inher…
Information-Theoretic Decentralized Secure Aggregation with Passive Collusion Resilience
Xiang Zhang, Zhou Li, Shuangyang Li +3
In decentralized federated learning (FL), multiple clients collaboratively learn a shared machine learning (ML) model by leveraging their privately held datasets distributed across…