Adversarial Robustness Toolbox v1.0.0
arXiv:1807.01069
Abstract
Adversarial Robustness Toolbox (ART) is a Python library supporting developers and researchers in defending Machine Learning models (Deep Neural Networks, Gradient Boosted Decision Trees, Support Vector Machines, Random Forests, Logistic Regression, Gaussian Processes, Decision Trees, Scikit-learn Pipelines, etc.) against adversarial threats and helps making AI systems more secure and trustworthy. Machine Learning models are vulnerable to adversarial examples, which are inputs (images, texts, tabular data, etc.) deliberately modified to produce a desired response by the Machine Learning model. ART provides the tools to build and deploy defences and test them with adversarial attacks. Defending Machine Learning models involves certifying and verifying model robustness and model hardening with approaches such as pre-processing inputs, augmenting training data with adversarial samples, and leveraging runtime detection methods to flag any inputs that might have been modified by an adversary. The attacks implemented in ART allow creating adversarial attacks against Machine Learning models which is required to test defenses with state-of-the-art threat models. Supported Machine Learning Libraries include TensorFlow (v1 and v2), Keras, PyTorch, MXNet, Scikit-learn, XGBoost, LightGBM, CatBoost, and GPy. The source code of ART is released with MIT license at https://github.com/IBM/adversarial-robustness-toolbox. The release includes code examples, notebooks with tutorials and documentation (http://adversarial-robustness-toolbox.readthedocs.io).
arXiv comment34 pages
Cited by in corpus (7)
- The Limitations of Model Uncertainty in Adversarial Settings
- Measuring the Transferability of Adversarial Examples
- RAID: Randomized Adversarial-Input Detection for Neural Networks
- Automated Discovery of Adaptive Attacks on Adversarial Defenses
- Exploring the Hyperparameter Landscape of Adversarial Robustness
- DiPSeN: Differentially Private Self-normalizing Neural Networks For Adversarial Robustness in Federated Learning
- Attack Transferability Characterization for Adversarially Robust Multi-label Classification