DeepMind's Tacotron-2 Tensorflow implementation

Everything Deepfakes

💀 A collection of methods to fool the deep neural network 💀

full tensorflow implementation of the paper: StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks https://arxiv.org/abs/1806.02169

AdvBox是一款由百度安全实验室研发，在百度大范围使用的AI模型安全工具箱，目前原生支持PaddlePaddle、PyTorch、Caffe2、MxNet、Keras以及TensorFlow平台，方便广大开发者和安全工程师可以使用自己熟悉的框架。 AdvBox同时支持GraphPipe,屏蔽了底层使用的深度学习平台，用户可以通过几个命令就可以对PaddlePaddle、PyTorch、Ca…

This is now the official location of the Kaldi project.

Code for "Black-box Adversarial Attacks with Limited Queries and Information" (http://arxiv.org/abs/1804.08598)

This library provides common speech features for ASR including MFCCs and filterbank energies.

Speaker identification with VGGVox network

Metasploit Framework

Extract xvector and ivector under kaldi

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

Deep neural networks for voice conversion (voice style transfer) in Tensorflow

Targeted Adversarial Examples on Speech-to-Text systems

A CNN model for code generation.

A list of all named GANs!

The classical paper list with code about generative adversarial nets

This project is a speaker recognition system which uses GMM, GMM-UBM and i-vector identifier

Realization of paper: "Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN" 2017

For macOS.百度网盘 破解SVIP、下载速度限制~

For macOS。Mac版 迅雷的反hook绕过~

Targeted Adversarial Examples for Black Box Audio Systems

Machine Learning course project to convert a source voice into a target voice.

Thanks VGGVox Oxford Model for the Speaker Recognition model generation. We would like to port to Python for realtime running

Code repository for the paper "Adversarial Deep Learning for Robust Detection of Binary Encoded Malware"

Larger resolution face masked, weirdly warped, deepfake,