Adversarial Robustness Toolbox v1.0.0

By Maria-Irina Nicolae, Mathieu Sinn, Minh-Ngoc Tran, Beat Buesser, Ambrish Rawat, Martin Wistuba, Valentina Zantedeschi, Nathalie Baracaldo, Bryant Chen, Heiko Ludwig and 2 more. 2018

573 citations recorded by the source corpus.

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 (this http URL).

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering (2018, methodology): “We implemented and released our method through the open source IBM Adversarial Robustness Toolbox (Nico-lae et al., 2018).”
Increasing Trust in AI Services through Supplier's Declarations of Conformity (2018, background): “Services may be instrumented to detect such attacks and may also be designed with defenses to be resilient [40].”
FactSheets: Increasing trust in AI services through supplier's declarations of conformity (2019, background): “Services may be instrumented to detect such attacks and may also be designed with defenses [46].”
RobustBench: a standardized adversarial robustness benchmark (2020, background): “However, some training techniques like MART [148] can noticeably increase the RSD and thus increase the disparity compared to other methods which achieve similar robustness (around 57%).”
Behavioral Use Licensing for Responsible AI (2020, methodology): “In addition, behavioral testing frameworks [56] have been developed, including those that adversarially attack machine learning models to assess their sensitivity to input features [48], alongside various other tools3 that help visualize the processing of inputs in an AI system.”
secml: A Python Library for Secure and Explainable Machine Learning (2019, background): “With respect to other popular libraries that implement attacks almost solely against DNNs (Papernot et al., 2018; Rauber et al., 2017; Nicolae et al., 2018), secml also implements training-time poisoning attacks and computationally-eﬃcient test-time evasion attacks against many diﬀerent algorithms,…”