activity
20242026
collaborators

6 papers

cs.DS2026

Convex Optimization with Local Label Differential Privacy: Tight Bounds in All Privacy Regimes

Lynn Chua, Badih Ghazi, Ravi Kumar +3

We study the problem of Stochastic Convex Optimization (SCO) under the constraint of local Label Differential Privacy (L-LDP). In this setting, the features are considered public,…

cs.CR2025

VaultGemma: A Differentially Private Gemma Model

Amer Sinha, Thomas Mesnard, Ryan McKenna +18

We introduce VaultGemma 1B, a 1 billion parameter model within the Gemma family, fully trained with differential privacy. Pretrained on the identical data mixture used for the Gemm…

cs.LG2025

Balls-and-Bins Sampling for DP-SGD

Lynn Chua, Badih Ghazi, Charlie Harrison +6

We introduce the Balls-and-Bins sampling for differentially private (DP) optimization methods such as DP-SGD. While it has been common practice to use some form of shuffling in DP-…

cs.CL2025

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models

Lynn Chua, Badih Ghazi, Yangsibo Huang +6

Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, i.e…

cs.LG2024

Scalable DP-SGD: Shuffling vs. Poisson Subsampling

Lynn Chua, Badih Ghazi, Pritish Kamath +4

We provide new lower bounds on the privacy guarantee of the multi-epoch Adaptive Batch Linear Queries (ABLQ) mechanism with shuffled batch sampling, demonstrating substantial gaps…

cs.CR2024

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy

Yangsibo Huang, Daogao Liu, Lynn Chua +7

Machine unlearning algorithms, designed for selective removal of training data from models, have emerged as a promising approach to growing privacy concerns. In this work, we expos…