Source code and demo for INTERPSEECH 2023 paper: DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model

Image restoration with neural networks but without learning.

Official Repository for the CVPR 2020 paper "Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs"

Aty-TTS: Improving fairness for spoken language understanding in atypical speech with Text-to-Speech

The Implementation of FastSpeech based on pytorch.

Fork of Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

Fork of Official PyTorch implementation of StyleGAN3

Fork of StudioGAN which is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

Ensembling Off-the-shelf Models for GAN Training (CVPR 2022 Oral)

A list of backdoor learning resources

competition

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

Invisible Backdoor Attack with Sample-Specific Triggers

Source code for paper "How to Backdoor Federated Learning" (https://arxiv.org/abs/1807.00459)