Prioritized Experience Replay (PER) implementation in PyTorch

A new adversarial purification method that uses the forward and reverse processes of diffusion models to remove adversarial perturbations.

Semi-supervised GAN in "Improved Techniques for Training GANs"

Code implementation of the paper "Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks", at IEEE Security and Privacy 2019.

TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.

MNIST converted to PNG format

A tensorflow implementation of "Accurate Image Super-Resolution Using Very Deep Convolutional Networks", CVPR 16'

Source code for the paper "Active Prompting with Chain-of-Thought for Large Language Models"

Code for Hierarchical Discrete Distribution Decomposition for Match Density Estimation (CVPR 2019)

Pytorch implementation of Deep Variational Information Bottleneck

Official repository for our NeurIPS 2023 paper "Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense" (https://arxiv.org/abs/2303.13408).

Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"

Code for the ACL-2022 paper "Knowledge Neurons in Pretrained Transformers"

[NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.

There is the semi-supervised implement of 'Improved Techniques for Training GANs '

Instagram-like image filters

Tensorflow implementation of the paper "Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution"

A repository to quickly generate synthetic data and associated trojaned deep learning models

Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"

Code, datasets, models for the paper "Automatic Evaluation of Attribution by Large Language Models"

Code for experiments in 'Primal Dual Formulation For Deep Learning With Constraints'

Improved Techniques for Training GANs for cifar10 dataset

Improving Robustness to Model Inversion Attacks via Mutual Information Regularization (AAAI 2021)