Yinpeng Dong

Non-Targeted-Adversarial-Attacks. A non-targeted adversarial attack method, which won the first place in NIPS 2017 non-targeted adversarial attacks competition

Translation-Invariant-Attacks. The translation-invariant adversarial attack method to improve the transferability of adversarial examples.

Targeted-Adversarial-Attack. A targeted adversarial attack method, which won the NIPS 2017 targeted adversarial attacks competition

Stochastic-Quantization. Training Low-bits DNNs with Stochastic Quantization

Adversarial-Distributional-Training. Adversarial Distributional Training (NeurIPS 2020)

Robust-and-Explainable-Machine-Learning. Related materials for robust and explainable machine learning

memorization-AT. Python

os_lab. C

dongyp13.github.io. HTML

ViewFool_. This repository contains the ViewFool and ImageNet-V proposed by the paper “ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints” (NeurIPS2022).

Face-Robustness-Benchmark. Python

video-caption. Python

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

DI-2-FGSM. Improving Transferability of Adversarial Examples with Input Diversity

awesome-adversarial-machine-learning. A curated list of awesome adversarial machine learning resources

MMLDA. A Strong and Efficient Adversarial Defense

youtube-8m. Python

MMTrustEval. A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust)

foolbox. Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, Keras, …

B3D.

place-attention. Python

RCE. Reverse Cross Entropy Training

adversarial-robustness-benchmark. Python