4 papers
Breaking Privacy in Federated Clustering: Perfect Input Reconstruction via Temporal Correlations
Guang Yang, Lixia Luo, Qiongxiu Li
Federated clustering allows multiple parties to discover patterns in distributed data without sharing raw samples. To reduce overhead, many protocols disclose intermediate centroid…
Deterministic Algorithms to Solve the -Complete Hidden Subset Sum Problem
Lixia Luo, Changheng Li, Qiongxiu Li
The Hidden Subset Sum Problem (HSSP) is a significant NP-complete problem in number theory and combinatorics, with applications in cryptography and AI privacy. For the -comp…
Perfect Gradient Inversion in Federated Learning: A New Paradigm from the Hidden Subset Sum Problem
Qiongxiu Li, Lixia Luo, Agnese Gini +6
Federated Learning (FL) has emerged as a popular paradigm for collaborative learning among multiple parties. It is considered privacy-friendly because local data remains on persona…
On the privacy of federated Clustering: A Cryptographic View
Qiongxiu Li, Lixia Luo
The privacy concern in federated clustering has attracted considerable attention in past decades. Many privacy-preserving clustering algorithms leverage cryptographic techniques li…