Constant matters: Fine-grained error bound on differentially private continual observation
H Fichtenberger, M Henzinger… - … on Machine Learning, 2023 - proceedings.mlr.press
We study fine-grained error bounds for differentially private algorithms for counting under
continual observation. Our main insight is that the matrix mechanism when using lower …
continual observation. Our main insight is that the matrix mechanism when using lower …
Exact optimality of communication-privacy-utility tradeoffs in distributed mean estimation
We study the mean estimation problem under communication and local differential privacy
constraints. While previous work has proposed order-optimal algorithms for the same …
constraints. While previous work has proposed order-optimal algorithms for the same …
Almost tight error bounds on differentially private continual counting
The first large-scale deployment of private federated learning uses differentially private
counting in the continual release model as a subroutine (Google AI blog titled “Federated …
counting in the continual release model as a subroutine (Google AI blog titled “Federated …
Fast optimal locally private mean estimation via random projections
We study the problem of locally private mean estimation of high-dimensional vectors in the
Euclidean ball. Existing algorithms for this problem either incur sub-optimal error or have …
Euclidean ball. Existing algorithms for this problem either incur sub-optimal error or have …
Optimal differentially private learning with public data
Differential Privacy (DP) ensures that training a machine learning model does not leak
private data. However, the cost of DP is lower model accuracy or higher sample complexity …
private data. However, the cost of DP is lower model accuracy or higher sample complexity …
Privacy Preserving Semi-Decentralized Mean Estimation over Intermittently-Connected Networks
We consider the problem of privately estimating the mean of vectors distributed across
different nodes of an unreliable wireless network, where communications between nodes …
different nodes of an unreliable wireless network, where communications between nodes …
Private federated learning with autotuned compression
E Ullah, CA Choquette-Choo… - … on Machine Learning, 2023 - proceedings.mlr.press
We propose new techniques for reducing communication in private federated learning
without the need for setting or tuning compression rates. Our on-the-fly methods …
without the need for setting or tuning compression rates. Our on-the-fly methods …
Privacy-aware compression for federated learning through numerical mechanism design
In private federated learning (FL), a server aggregates differentially private updates from a
large number of clients in order to train a machine learning model. The main challenge in …
large number of clients in order to train a machine learning model. The main challenge in …
Multi-message shuffled privacy in federated learning
We study the distributed mean estimation (DME) problem under privacy and communication
constraints in the local differential privacy (LDP) and multi-message shuffled (MMS) privacy …
constraints in the local differential privacy (LDP) and multi-message shuffled (MMS) privacy …
Federated Deep Reinforcement Learning-Based Intelligent Surface Configuration in 6G Secure Airport Networks
Y Chen, S Al-Rubaye, A Tsourdos… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Reconfigurable Intelligent Surface (RIS) is envisioned to revolutionize 6G wireless networks,
particularly in complex environments like smart airports, by customizing analog …
particularly in complex environments like smart airports, by customizing analog …