Robust Machine Learning Python Packages

mrcpy

A Library for Minimax Risk Classifiers

pydvl

pyDVL is a library of stable implementations of algorithms for data valuation and influence function computation

robustsignalmaker

NaN-aware, leakage-free stability selection for scientific signals and spectra

scikit-clean

A collection of algorithms for detecting and handling label noise

blades

⚔️ Blades: A Unified Benchmark Suite for Attacks and Defenses in Federated Learning

robustloss-lab

A Python library for robust classification losses (CCE/SCCE, Focal, GCE) with reproducible outlier and noise experiments

robust-deep-learning

A project to train your model from scratch or fine-tune a pretrained model using the losses provided in this library to improve out-of-distribution detection and uncertainty estimation performances. Calibrate your model to produce enhanced uncertainty estimations. Detect out-of-distribution data using the defined score type and threshold.