activity
20122024
most citedEncode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation

36 citations · 133 across the 15 of their papers we have counts for

collaborators

20 papers

cs.LG20222 cited

Differentially Private Image Classification from Features

Harsh Mehta, Walid Krichene, Abhradeep Thakurta +2

Leveraging transfer learning has recently been shown to be an effective strategy for training large models with Differential Privacy (DP). Moreover, somewhat surprisingly, recent w…

cs.CR2022

Fully Adaptive Composition for Gaussian Differential Privacy

Adam Smith, Abhradeep Thakurta

We show that Gaussian Differential Privacy, a variant of differential privacy tailored to the analysis of Gaussian noise addition, composes gracefully even in the presence of a ful…

cs.LG20225 cited

Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search

Yannis Cattan, Christopher A. Choquette-Choo, Nicolas Papernot +1

Models need to be trained with privacy-preserving learning algorithms to prevent leakage of possibly sensitive information contained in their training data. However, canonical algo…

cs.LG20225 cited

Large Scale Transfer Learning for Differentially Private Image Classification

Harsh Mehta, Abhradeep Thakurta, Alexey Kurakin +1

Differential Privacy (DP) provides a formal framework for training machine learning models with individual example level privacy. In the field of deep learning, Differentially Priv…

cs.LG202221 cited

Toward Training at ImageNet Scale with Differential Privacy

Alexey Kurakin, Shuang Song, Steve Chien +3

Differential privacy (DP) is the de facto standard for training machine learning (ML) models, including neural networks, while ensuring the privacy of individual examples in the tr…

cs.LG20211 cited

Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates

Steve Chien, Prateek Jain, Walid Krichene +4

We study the problem of differentially private (DP) matrix completion under user-level privacy. We design a joint differentially private variant of the popular Alternating-Least-Sq…