David W. Trott's Projects
Keras implementation of AdvGAN by Xiao et al. (2018) https://arxiv.org/abs/1801.02610
Adv-GAN: Generator, Discriminator and Adversarial Attacker
a Pytorch implementation of the paper "Generating Adversarial Examples with Adversarial Networks" (advGAN).
The official implementation of our paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".
First course in GAN Specialization
CSCI 6464/4364 Machine Learning Spring 2021
The Leek group guide to data sharing
Graph Convolution Network for PyTorch
The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".