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

April 3, 2022

A Differentially Private Framework for Deep Learning with Convexified Loss Functions
Zhigang Lu, Hassan Jameel Asghar, Mohamed Ali Kaafar, Darren Webb, Peter Dickinson
Deep Learning Differential Privacy Private Stochastic Differential Privacy SGD Convex Loss Function Agentive Permission

April 2, 2022

Production of Categorical Data Verifying Differential Privacy: Conception and Applications to Machine Learning
Héber H. Arcolezi
Machine Learning Financial Application Differential Privacy Privacy Preserving Production Incident Private Machine Learning Privacy Utility Trade Novel Concept

March 30, 2022

March 24, 2022

Statistic Selection and MCMC for Differentially Private Bayesian Estimation
Baris Alparslan, Sinan Yildirim
Differential Privacy Text Privatization Bayesian Estimation Private Bayesian

March 22, 2022

Mixed Differential Privacy in Computer Vision
Aditya Golatkar, Alessandro Achille, Yu-Xiang Wang, Aaron Roth, Michael Kearns, Stefano Soatto
Computer Vision Differential Privacy Privacy Guarantee Private Algorithm Private Datasets Private Fine Tuning

March 18, 2022

Privacy-Preserving Reinforcement Learning Beyond Expectation
Arezoo Rajabi, Bhaskar Ramasubramanian, Abdullah Al Maruf, Radha Poovendran
Reinforcement Learning Autonomous Vehicle Differential Privacy Privacy Utility Expectation Alignment Prospect Theory

March 17, 2022

March 15, 2022

Training a Tokenizer for Free with Private Federated Learning
Eugene Bagdasaryan, Congzheng Song, Rogier van Dalen, Matt Seigel, Áine Cahill
Differential Privacy Private Data Private Federated Learning Online Tokenizer

March 13, 2022

March 10, 2022

March 7, 2022

Differential Privacy

Papers

A Differentially Private Framework for Deep Learning with Convexified Loss Functions

Production of Categorical Data Verifying Differential Privacy: Conception and Applications to Machine Learning

Towards Differential Relational Privacy and its use in Question Answering

Decentralized Collaborative Learning Framework for Next POI Recommendation

Statistic Selection and MCMC for Differentially Private Bayesian Estimation

Mixed Differential Privacy in Computer Vision

Privacy-Preserving Reinforcement Learning Beyond Expectation

Decouple-and-Sample: Protecting sensitive information in task agnostic data release

SoK: Differential Privacy on Graph-Structured Data

Training a Tokenizer for Free with Private Federated Learning

Private Non-Convex Federated Learning Without a Trusted Server

One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy

Fully Adaptive Composition in Differential Privacy

Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)

Similarity-based Label Inference Attack against Training and Inference of Split Learning

The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning

Differential Privacy Amplification in Quantum and Quantum-inspired Algorithms

Continual and Sliding Window Release for Private Empirical Risk Minimization

Quantum Local Differential Privacy and Quantum Statistical Query Model

Differentially Private Federated Learning with Local Regularization and Sparsification