Badih Ghazi

Private Hyperparameter Tuning with Ex-Post Guarantee

Scaling Embedding Layers in Language Models

Quantifying Cross-Modality Memorization in Vision-Language Models

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models

URANIA: Differentially Private Insights into AI Use

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models

Scaling Embedding Layers in Language Models

Scaling Laws for Differentially Private Language Models

On Memorization of Large Language Models in Logical Reasoning

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning

Differentially Private Optimization with Sparse Gradients

LabelDP-Pro: Learning with Label Differential Privacy via Projections

Scalable DP-SGD: Shuffling vs. Poisson Subsampling

Patio: Framework for Private Release of Ratios