Related papers: The Skellam Mechanism for Differentially Private F…
Differentially private stochastic gradient descent (DP-SGD) is the workhorse algorithm for recent advances in private deep learning. It provides a single privacy guarantee to all datapoints in the dataset. We propose output-specific…
A key tool for building differentially private systems is adding Gaussian noise to the output of a function evaluated on a sensitive dataset. Unfortunately, using a continuous distribution presents several practical challenges. First and…
This paper introduces a differentially private mechanism to protect the information exchanged during the coordination of the sequential market-clearing of electricity and natural gas systems. The coordination between these sequential and…
Achieving differential privacy (DP) guarantees in fully decentralized machine learning is challenging due to the absence of a central aggregator and varying trust assumptions among nodes. We present a framework for DP analysis of…
Differentially Private Stochastic Gradient Descent (DP-SGD) forms a fundamental building block in many applications for learning over sensitive data. Two standard approaches, privacy amplification by subsampling, and privacy amplification…
In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial examples. We first relax the constraint of the privacy budget in…
We present an asymptotically optimal $(\epsilon,\delta)$ differentially private mechanism for answering multiple, adaptively asked, $\Delta$-sensitive queries, settling the conjecture of Steinke and Ullman [2020]. Our algorithm has a…
Differential privacy provides a rigorous framework to quantify data privacy, and has received considerable interest recently. A randomized mechanism satisfying $(\epsilon, \delta)$-differential privacy (DP) roughly means that, except with a…
Federated learning enhanced with Differential Privacy (DP) is a powerful privacy-preserving strategy to protect individuals sharing their sensitive data for processing in fields such as medicine and healthcare. Many medical applications,…
Differentially private stochastic gradient descent (DP-SGD) is a standard approach to privacy-preserving learning based on per-example clipping, subsampling, Gaussian perturbation, and privacy accounting. Classical DP-SGD releases a noisy…
In privacy-preserving machine learning, individual parties are reluctant to share their sensitive training data due to privacy concerns. Even the trained model parameters or prediction can pose serious privacy leakage. To address these…
Differentially private federated learning faces a fundamental tension: privacy protection mechanisms that safeguard client data simultaneously create quantifiable privacy costs that discourage participation, undermining the collaborative…
Split learning is a distributed training framework that allows multiple parties to jointly train a machine learning model over vertically partitioned data (partitioned by attributes). The idea is that only intermediate computation results,…
Federated learning is distributed model training across several clients without disclosing raw data. Despite advancements in data privacy, risks still remain. Differential Privacy (DP) is a technique to protect sensitive data by adding…
Developing machine learning methods that are privacy preserving is today a central topic of research, with huge practical impacts. Among the numerous ways to address privacy-preserving learning, we here take the perspective of computing the…
Differentially private federated learning (DP-FL) is a promising technique for collaborative model training while ensuring provable privacy for clients. However, optimizing the tradeoff between privacy and accuracy remains a critical…
Communication and privacy are two critical concerns in distributed learning. Many existing works treat these concerns separately. In this work, we argue that a natural connection exists between methods for communication reduction and…
Differential privacy is a notion of privacy that has become very popular in the database community. Roughly, the idea is that a randomized query mechanism provides sufficient privacy protection if the ratio between the probabilities that…
The popularity of federated learning comes from the possibility of better scalability and the ability for participants to keep control of their data, improving data security and sovereignty. Unfortunately, sharing model updates also creates…
We study privacy in a distributed learning framework, where clients collaboratively build a learning model iteratively through interactions with a server from whom we need privacy. Motivated by stochastic optimization and the federated…