Differentially private vertical federated clustering
Z Li, T Wang, N Li - ar** in DP‐SGD, empirically
G Lin, H Yan, G Kou, T Huang, S Peng… - … Journal of Intelligent …, 2022 - Wiley Online Library
Abstract Differentially Private Stochastic Gradient Descent (DP‐SGD) is a prime method for
training machine learning models with rigorous privacy guarantees. Since its birth, DP‐SGD …
training machine learning models with rigorous privacy guarantees. Since its birth, DP‐SGD …
Dealing Doubt: Unveiling Threat Models in Gradient Inversion Attacks under Federated Learning, A Survey and Taxonomy
Federated Learning (FL) has emerged as a leading paradigm for decentralized, privacy
preserving machine learning training. However, recent research on gradient inversion …
preserving machine learning training. However, recent research on gradient inversion …
Differentially Private Distributed Frequency Estimation
In order to remain competitive, Internet companies collect and analyse user data for the
purpose of the improvement of user experiences. Frequency estimation is a widely used …
purpose of the improvement of user experiences. Frequency estimation is a widely used …
Kvsagg: Secure aggregation of distributed key-value sets
In global data analysis, the central server needs the global statistic of the user data stored in
local clients. In such cases, an Honest-but-Curious central server might put user privacy at …
local clients. In such cases, an Honest-but-Curious central server might put user privacy at …
The opportunity in difficulty: A dynamic privacy budget allocation mechanism for privacy-preserving multi-dimensional data collection
Data collection under local differential privacy (LDP) has been gradually on the stage.
Compared with the implementation of LDP on the single attribute data collection, that on …
Compared with the implementation of LDP on the single attribute data collection, that on …
Federated heavy hitter recovery under linear sketching
Motivated by real-life deployments of multi-round federated analytics with secure
aggregation, we investigate the fundamental communication-accuracy tradeoffs of the heavy …
aggregation, we investigate the fundamental communication-accuracy tradeoffs of the heavy …
Generation of high-order random key matrix for Hill Cipher encryption using the modular multiplicative inverse of triangular matrices
Y Chen, R **e, H Zhang, D Li, W Lin - Wireless Networks, 2024 - Springer
Hill Cipher is one of the classic symmetric encryption algorithms widely used in cloud data
security. Although the hill cipher principle is relatively simple, its key matrix must be …
security. Although the hill cipher principle is relatively simple, its key matrix must be …
Split, count, and share: a differentially private set intersection cardinality estimation protocol
We describe a simple two-party protocol in which each party contributes a set as input. The
output of the protocol is an estimate of the cardinality of the intersection of the two input sets …
output of the protocol is an estimate of the cardinality of the intersection of the two input sets …
An effective and differentially private protocol for secure distributed cardinality estimation
Counting the number of distinct elements distributed over multiple data holders is a
fundamental problem with many real-world applications ranging from crowd counting to …
fundamental problem with many real-world applications ranging from crowd counting to …