-
equational_theories Public
Forked from teorth/equational_theoriesA project to map out the relations between different equational theories of Magmas.
-
A benchmark to evaluate language models on questions I've previously asked them to solve.
-
Adv360-Pro-ZMK Public
Forked from KinesisCorporation/Adv360-Pro-ZMKProduction repository for the all-new Advantage360 Professional using ZMK engine
-
chess-llm Public
Play chess against large language models.
-
arduino-apple-profile-reader Public
A short script to read data off of an Apple ProFile hard drive with an Arduino.
-
-
Yet another doom clone (in 13kb of JavaScript)
-
img2dataset Public
Forked from rom1504/img2datasetEasily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
-
audio_adversarial_examples Public
Targeted Adversarial Examples on Speech-to-Text systems
-
-
printf-tac-toe Public
tic-tac-toe in a single call to printf
-
open_clip Public
Forked from mlfoundations/open_clipAn open source implementation of CLIP.
Python Other UpdatedMay 5, 2022 -
privacy Public
Forked from tensorflow/privacyLibrary for training machine learning models with privacy for training data
-
backpropagation-clipping Public
Forked from uvm-plaid/backpropagation-clippingPython UpdatedFeb 12, 2022 -
-
nn_robust_attacks Public
Robust evasion attacks against neural network to find adversarial examples
-
-
-
gpt-2 Public
Forked from openai/gpt-2Code for the paper "Language Models are Unsupervised Multitask Learners"
Python MIT License UpdatedJul 13, 2020 -
cleverhans Public
Forked from cleverhans-lab/cleverhansA library for benchmarking vulnerability to adversarial examples
-
adv-eval-paper Public
Forked from evaluating-adversarial-robustness/adv-eval-paperLaTeX source for the paper "On Evaluating Adversarial Robustness"
-
ImageNet-Adversarial-Training Public
Forked from facebookresearch/ImageNet-Adversarial-TrainingFeature Denoising for Improving Adversarial Robustness
Python Other UpdatedFeb 8, 2019 -
AmI Public
Forked from Gwinhen/AmIAttacks Meet Interpretability
-
foolbox Public
Forked from bethgelab/foolboxPython toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, Keras, …
-
MagNet Public
Forked from Trevillie/MagNetMagNet: a Two-Pronged Defense against Adversarial Examples
-
pixel-deflection Public
Forked from iamaaditya/pixel-deflectionDeflecting Adversarial Attacks with Pixel Deflection
-
nmt Public
Forked from tensorflow/nmtTensorFlow Neural Machine Translation Tutorial
-
breaking_efficient_defenses Public
Code to reproduce and break the "Efficient Defenses" paper
-
APE-GAN Public
Forked from shenqixiaojiang/APE-GANTensorflow implementation of Our APE-GAN
-
nn_breaking_detection Public
Code corresponding to the paper "Adversarial Examples are not Easily Detected..."