Princeton-SysML

GradAttack

GradAttack is a Python library for easy evaluation of privacy risks in public gradients in Federated Learning, as well as corresponding mitigation strategies.

Jailbreak_LLM

FILM

Official repo for the paper: Recovering Private Text in Federated Learning of Language Models (in NeurIPS 2022)

kNNLM_privacy

Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888

jailbreak-llm