ART swMATH ID: 37566 Software Authors: The Adversarial Robustness Toolbox (ART) Authors; Beat Buesser; et al. Description: Adversarial Robustness Toolbox (ART) is a Python library for Machine Learning Security. ART provides tools that enable developers and researchers to defend and evaluate Machine Learning models and applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference. ART supports all popular machine learning frameworks (TensorFlow, Keras, PyTorch, MXNet, scikit-learn, XGBoost, LightGBM, CatBoost, GPy, etc.), all data types (images, tables, audio, video, etc.) and machine learning tasks (classification, object detection, speech recognition, generation, certification, etc.). Homepage: https://adversarial-robustness-toolbox.readthedocs.io/en/latest/ Source Code: https://github.com/Trusted-AI/adversarial-robustness-toolbox Dependencies: Python Related Software: Advbox; Model Zoo; Februus; BadNets; TrojAI; TrojDRL; DEEPSEC; MagNet; cleverhans; VGGFace2; ImageNet; CIFAR; PyTorch; Python; TrojanZoo; Grad-CAM; KFServing; TensorFlow; Katib; Jupyter Cited in: 0 Publications