gwinhen Goto Github PK

ami

This repository is for NeurIPS 2018 spotlight paper "Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples."

backdoorvault

A toolbox for backdoor attacks.

drupe

Distribution Preserving Backdoor Attack in Self-supervised Learning

hardbeat

This is the repository for USENIX Security 2023 paper "Hard-label Black-box Universal Adversarial Patch Attack".

mmdnn

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

moth

This is the implementation for IEEE S&P 2022 paper "Model Orthogonalization: Class Distance Hardening in Neural Networks for Better Security."

pixelbackdoor

This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."

pytorch-cifar

95.47% on CIFAR10 with PyTorch

rose6icse

ruler

Repository for FSE 2022 Paper "RULER: Discriminative and Iterative Adversarial Training for Deep Neural Network Fairness"

trader

This is the repository for ICSE 2020 paper "TRADER: Trace Divergence Analysis and Embedding Regulation for Debugging Recurrent Neural Networks."