Comprehensive-Tacotron2PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supports both single-, multi-speaker TTS and several techniques to enforce the robustness and efficiency of the model.
square-attackSquare Attack: a query-efficient black-box adversarial attack via random search [ECCV 2020]
GeFsGenerative Forests in Python
DiagnoseRESource code and dataset for the CCKS201 paper "On Robustness and Bias Analysis of BERT-based Relation Extraction"
belayRobust error-handling for Kotlin and Android
RaySRayS: A Ray Searching Method for Hard-label Adversarial Attack (KDD2020)
perceptual-advexCode and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".
s-attack[CVPR 2022] S-attack library. Official implementation of two papers "Vehicle trajectory prediction works, but not everywhere" and "Are socially-aware trajectory prediction models really socially-aware?".
shortcut-perspectiveFigures & code from the paper "Shortcut Learning in Deep Neural Networks" (Nature Machine Intelligence 2020)
robustness-vitContains code for the paper "Vision Transformers are Robust Learners" (AAAI 2022).
cycle-confusionCode and models for ICCV2021 paper "Robust Object Detection via Instance-Level Temporal Cycle Confusion".
Generalization-Causality关于domain generalization,domain adaptation,causality,robutness,prompt,optimization,generative model各式各样研究的阅读笔记
eleanorCode used during my Chaos Engineering and Resiliency Patterns talk.
TIGERPython toolbox to evaluate graph vulnerability and robustness (CIKM 2021)
ATMC[NeurIPS'2019] Shupeng Gui, Haotao Wang, Haichuan Yang, Chen Yu, Zhangyang Wang, Ji Liu, “Model Compression with Adversarial Robustness: A Unified Optimization Framework”
DUNCode for "Depth Uncertainty in Neural Networks" (https://arxiv.org/abs/2006.08437)
safe-control-gymPyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL
CIL-ReIDBenchmarks for Corruption Invariant Person Re-identification. [NeurIPS 2021 Track on Datasets and Benchmarks]
aileen-coreSensor data aggregation tool for any numerical sensor data. Robust and privacy-friendly.
robust-gcnImplementation of the paper "Certifiable Robustness and Robust Training for Graph Convolutional Networks".
adversarial-robustness-publicCode for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"
POPQORNAn Algorithm to Quantify Robustness of Recurrent Neural Networks
SimP-GCNImplementation of the WSDM 2021 paper "Node Similarity Preserving Graph Convolutional Networks"
Denoised-Smoothing-TFMinimal implementation of Denoised Smoothing (https://arxiv.org/abs/2003.01908) in TensorFlow.
ViTs-vs-CNNs[NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)
spatial-smoothing(ICML 2022) Official PyTorch implementation of “Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness”.
pre-trainingPre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)
recentrifugeRecentrifuge: robust comparative analysis and contamination removal for metagenomics