4 citations · 10 across the 7 of their papers we have counts for
12 papers · 1 filter
Efficient DP-SGD for LLMs with Randomized Clipping
Enayat Ullah, Sai Aparna Aketi, Devansh Gupta +2
Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Differential privacy (DP), the de facto standard for formal privacy guarantees, pr…
Synthetic Tabular Data: Methods, Attacks and Defenses
Graham Cormode, Samuel Maddock, Enayat Ullah +1
Synthetic data is often positioned as a solution to replace sensitive fixed-size datasets with a source of unlimited matching data, freed from privacy concerns. There has been much…
Public-data Assisted Private Stochastic Optimization: Power and Limitations
Enayat Ullah, Michael Menart, Raef Bassily +2
We study the limits and capability of public-data assisted differentially private (PA-DP) algorithms. Specifically, we focus on the problem of stochastic convex optimization (SCO)…
Differentially Private Non-Convex Optimization under the KL Condition with Optimal Rates
Michael Menart, Enayat Ullah, Raman Arora +2
We study private empirical risk minimization (ERM) problem for losses satisfying the -Kurdyka-Łojasiewicz (KL) condition. The Polyak-Łojasiewicz (PL) condition is a special…
From Adaptive Query Release to Machine Unlearning
Enayat Ullah, Raman Arora
We formalize the problem of machine unlearning as design of efficient unlearning algorithms corresponding to learning algorithms which perform a selection of adaptive queries from…
Private Federated Learning with Autotuned Compression
Enayat Ullah, Christopher A. Choquette-Choo, Peter Kairouz +1
We propose new techniques for reducing communication in private federated learning without the need for setting or tuning compression rates. Our on-the-fly methods automatically ad…