9 papers
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…
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…
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…
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…
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…
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…