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 …

Dealing Doubt: Unveiling Threat Models in Gradient Inversion Attacks under Federated Learning, A Survey and Taxonomy

Y Shi, O Kotevska, V Reshniak, A Singh… - arxiv preprint arxiv …, 2024 - arxiv.org
Federated Learning (FL) has emerged as a leading paradigm for decentralized, privacy
preserving machine learning training. However, recent research on gradient inversion …

Differentially Private Distributed Frequency Estimation

M Yang, I Tjuawinata, KY Lam, T Zhu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
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 …

Kvsagg: Secure aggregation of distributed key-value sets

Y Wu, S Dong, Y Zhou, Y Zhao, F Fu… - 2023 IEEE 39th …, 2023 - ieeexplore.ieee.org
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 …

The opportunity in difficulty: A dynamic privacy budget allocation mechanism for privacy-preserving multi-dimensional data collection

X Chen, C Wang, Q Yang, T Hu, C Jiang - ACM Transactions on …, 2023 - dl.acm.org
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 …

Federated heavy hitter recovery under linear sketching

A Gascon, P Kairouz, Z Sun… - … Conference on Machine …, 2023 - proceedings.mlr.press
Motivated by real-life deployments of multi-round federated analytics with secure
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 …

Split, count, and share: a differentially private set intersection cardinality estimation protocol

M Purcell, Y Li, KS Ng - Uncertainty in Artificial Intelligence, 2023 - proceedings.mlr.press
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 …

An effective and differentially private protocol for secure distributed cardinality estimation

P Wang, C Yang, D **e, J Zhao, H Li, J Tao… - Proceedings of the ACM …, 2023 - dl.acm.org
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 …