Differential Privacy

Differential privacy (DP) is a rigorous framework for ensuring data privacy in machine learning by adding carefully calibrated noise to model training processes. Current research focuses on improving the accuracy of DP models, particularly for large-scale training, through techniques like adaptive noise allocation, Kalman filtering for noise reduction, and novel gradient processing methods. This active area of research is crucial for enabling the responsible use of sensitive data in various applications, ranging from healthcare and finance to natural language processing and smart grids, while maintaining strong privacy guarantees.

Papers

June 27, 2022

Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization
Xiaodong Yang, Huishuai Zhang, Wei Chen, Tie-Yan Liu
Differential Privacy Gradient Norm Normalization Dictionary Small Perturbation Clipped Stochastic Gradient Descent Private Convex Optimization

June 24, 2022

Using Autoencoders on Differentially Private Federated Learning GANs
Gregor Schram, Rui Wang, Kaitai Liang
Differential Privacy Supervised Autoencoder GAN Model C Gan Private Federated Learning Privacy Sensitive

June 21, 2022

Differentially Private Maximal Information Coefficients
John Lazarsfeld, Aaron Johnson, Emmanuel Adeniran
Differential Privacy Mutual Information Private Data Private INFORMATION RETRIEVAL

June 20, 2022

Shuffle Gaussian Mechanism for Differential Privacy
Seng Pei Liew, Tsubasa Takahashi
Differential Privacy Shuffle Model Gaussian Mechanism

June 16, 2022

June 15, 2022

Disparate Impact in Differential Privacy from Gradient Misalignment
Maria S. Esipova, Atiyeh Ashari Ghomi, Yaqiao Luo, Jesse C. Cresswell
Differential Privacy Private Stochastic Gradient Descent Gradient Alignment Private Model Training Disparate Impact Fairness Loss

June 14, 2022

Self-Supervised Pretraining for Differentially Private Learning
Arash Asadian, Evan Weidner, Lei Jiang
Deep Learning Differential Privacy Self Supervised Pretraining Private Learning Private Datasets

June 12, 2022

Distributed Differential Privacy in Multi-Armed Bandits
Sayak Ray Chowdhury, Xingyu Zhou
Differential Privacy Multi Armed Bandit Shuffle Model Armed Bandit

June 10, 2022

June 9, 2022

June 7, 2022

Differential Privacy

Papers

Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization

Using Autoencoders on Differentially Private Federated Learning GANs

Differentially Private Maximal Information Coefficients

Shuffle Gaussian Mechanism for Differential Privacy

Introducing the Huber mechanism for differentially private low-rank matrix completion

On Privacy and Personalization in Cross-Silo Federated Learning

Disparate Impact in Differential Privacy from Gradient Misalignment

Self-Supervised Pretraining for Differentially Private Learning

Distributed Differential Privacy in Multi-Armed Bandits

Bayesian Estimation of Differential Privacy

Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging

Binarizing Split Learning for Data Privacy Enhancement and Computation Reduction

A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning

Analytical Composition of Differential Privacy via the Edgeworth Accountant

Subject Granular Differential Privacy in Federated Learning

Group privacy for personalized federated learning

Subject Membership Inference Attacks in Federated Learning

Privacy Amplification via Shuffled Check-Ins

A Privacy-Preserving Subgraph-Level Federated Graph Neural Network via Differential Privacy

Algorithms for bounding contribution for histogram estimation under user-level privacy