Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

Instruct-tune LLaMA on consumer hardware

An adversarial example library for constructing attacks, building defenses, and benchmarking both

Training PyTorch models with differential privacy

Contains high quality implementations of Deep Reinforcement Learning algorithms written in PyTorch

Awesome Machine Unlearning (A Survey of Machine Unlearning)

HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels

My attempt at reproducing the paper Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection

autodp: A flexible and easy-to-use package for differential privacy

A deep learning framework for synthesizing novel views of objects and scenes

Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"

Blackbox attacks for deep neural network models

Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''