Private Model

Private model research focuses on developing machine learning models that protect sensitive training data while maintaining high accuracy. Current efforts concentrate on techniques like differential privacy (DP), applied through algorithms such as DP-SGD and model-specific adaptations, and on leveraging public data or model ensembles to improve the privacy-utility trade-off. This field is crucial for responsible AI development, enabling the use of sensitive data in various applications while mitigating privacy risks and addressing fairness concerns arising from privacy-preserving methods.

Papers

October 28, 2022

Differential Privacy has Bounded Impact on Fairness in Classification
Paul Mangold, Michaël Perrot, Aurélien Bellet, Marc Tommasi
Classification Code Differential Privacy Procedural Fairness Group Fairness Private Model Lipschitz Operator

October 27, 2022

Anonymized Histograms in Intermediate Privacy Models
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Differential Privacy Histogram Layer Private Model Unlabeled Dataset Privacy Model Histogram Matching

April 22, 2022

Sharper Utility Bounds for Differentially Private Models
Yilin Kang, Yong Liu, Jian Li, Weiping Wang
Private Algorithm Private Model Lipschitz Bound Gradient Perturbation Bernstein Surface

March 5, 2022

The Impact of Differential Privacy on Group Disparity Mitigation
Victor Petrén Bach Hansen, Atula Tejaswi Neerkaje, Ramit Sawhney, Lucie Flek, Anders Søgaard
Differential Privacy Global Impact Procedural Fairness Empirical Risk Minimization Private Model Group Disparity Mitigating Disparity

February 16, 2022

Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams
Sergey Denisov, Brendan McMahan, Keith Rush, Adam Smith, Abhradeep Guha Thakurta
Differential Privacy Stochastic Gradient Descent Differential Privacy Guarantee Private Model User Level Differential Privacy Arch Factorization Private Linear

February 10, 2022

Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning
Alberto Bietti, Chen-Yu Wei, Miroslav Dudík, John Langford, Zhiwei Steven Wu
Differential Privacy Centralized Learning Generalization Guarantee Private Model Privacy Accuracy Federated Learning Algorithm

February 5, 2022

Training Differentially Private Models with Secure Multiparty Computation
Sikha Pentyala, Davis Railsback, Ricardo Maia, Rafael Dowsley, David Melanson, Anderson Nascimento, Martine De Cock
Training Data Differential Privacy Privacy Guarantee Private Model Secure Multiparty Computation Multi Party Computation

January 10, 2022

Differentially Private Generative Adversarial Networks with Model Inversion
Dongjie Chen, Sen-ching Samson Cheung, Chen-Nee Chuah, Sally Ozonoff
Generative Adversarial Network Model Inversion Private Model Private Generative Adversarial Network