Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

Natural Language Attacks in a Hard Label Black Box Setting.

Machine Learning and Computer Vision Engineer - Technical Interview Questions

Command-line program to download videos from YouTube.com and other video sites

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

WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)

Create adversarial attacks against machine learning Windows malware detectors

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

A PyTorch-based Speech Toolkit

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

Pytorch implementation of Conditional Image Synthesis with Auxiliary Classifier GANs

Code for the unrestricted adversarial examples paper (NeurIPS 2018)

RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

Source code for the paper "Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness"

A list of all named GANs!

A mix of GAN implementations including progressive growing

Jupyter Notebook for Human Activity Recognition (HAR) with 1D Convolutional Neural Network in Python and Keras

Code for paper "PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking"

GPT-3: Language Models are Few-Shot Learners

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

My entry for ICLR 2018 Reproducibility Challenge for paper Synthesizing robust adversarial examples https://openreview.net/pdf?id=BJDH5M-AW

Repository for Certified Defenses for Adversarial Patch ICLR-2020

Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's WaveNet and tensorflow

This repo is designed to gather bike share data best practices AND socialize a list of open and free tools to hack on bike share data. This grows from Council Member Brad Lander introducing Int. No…

Project to add mobility features to the Google Cardboard project. Inital plan is to use the onboard accelerometer, then move to other things.If I suceed, please clear the area around you before usi…

The official repository for Developing Android Apps

Open Source Computer Vision Library