activity
20242026
collaborators

9 papers

cs.LG2026

Memory-Efficient Differentially Private Training with Gradient Random Projection

Alex Mulrooney, Devansh Gupta, James Flemings +4

Differential privacy (DP) protects sensitive data during neural network training, but standard methods like DP-Adam suffer from high memory overhead due to per-sample gradient clip…

cs.CR2026

PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior

James Flemings, Murali Annavaram

Large language models (LLMs) are increasingly used to simulate human behavior, but their ability to simulate privacy decisions is not well understood. In this paper, w…

cs.LG2026

Fast NF4 Dequantization Kernels for Large Language Model Inference

Xiangbo Qi, Chaoyi Jiang, Murali Annavaram

Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFlo…

cs.CR2026

Personalizing Agent Privacy Decisions via Logical Entailment

James Flemings, Ren Yi, Octavian Suciu +3

Personal large language model (LLM) agents increasingly perform tasks that require access to user data, raising concerns about appropriate data disclosure. We show that relying sol…

cs.CL2025

Estimating Privacy Leakage of Augmented Contextual Knowledge in Language Models

James Flemings, Bo Jiang, Wanrong Zhang +2

Language models (LMs) rely on their parametric knowledge augmented with relevant contextual knowledge for certain tasks, such as question answering. However, the contextual knowled…

cs.LG2025

Differentially Private Knowledge Distillation via Synthetic Text Generation

James Flemings, Murali Annavaram

Large Language models (LLMs) are achieving state-of-the-art performance in many different downstream tasks. However, the increasing urgency of data privacy puts pressure on practit…