This is the code for FedHFT: Efficient Federated Finetuning with Heterogeneous Edge Clients (IEEE CogMI'25)

A survey on harmful fine-tuning attack for large language model

A Survey on Large Language Model-Based Game Agents

Code for CVPR24 Paper - Resource-Efficient Transformer Pruning for Finetuning of Large Models

This repo is for paper Securing Distributed SGD against Gradient Leakage Threats submitted to IEEE TPDS.

Code for GradCloak: Gradient Obfuscation for Privacy-Preserving Distributed Learning as a Service

This is the unofficial re-implementation of "Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack" (ICML2025)

GTLLMZoo: A comprehensive framework that aggregates LLM benchmark data from multiple sources with an interactive UI for efficient model comparison, filtering, and evaluation across performance, safety, and efficiency metrics.