Adversarial Robustness Toolbox v1.17 releases: crafting and analysis of attacks and defense methods for machine learning models
Adversarial Robustness Toolbox
Adversarial Robustness 360 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 to make 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 defenses 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 are required to test defenses with state-of-the-art threat models.
Supported attack and defense methods
The Adversarial Robustness Toolbox contains implementations of the following attacks:
- Deep Fool (Moosavi-Dezfooli et al., 2015)
- Fast Gradient Method (Goodfellow et al., 2014)
- Jacobian Saliency Map (Papernot et al., 2016)
- Universal Perturbation (Moosavi-Dezfooli et al., 2016)
- Virtual Adversarial Method (Moosavi-Dezfooli et al., 2015)
- C&W Attack (Carlini and Wagner, 2016)
- NewtonFool (Jang et al., 2017)
The following defense methods are also supported:
- Feature squeezing (Xu et al., 2017)
- Spatial smoothing (Xu et al., 2017)
- Label smoothing (Warde-Farley and Goodfellow, 2016)
- Adversarial training (Szegedy et al., 2013)
- Virtual adversarial training (Miyato et al., 2017)
The details of the work from IBM research can be found in the research paper. The ART toolbox is developed with the goal of helping developers better understand
- Measuring model robustness
- Model hardening
- Runtime detection
Changelog v1.17
This release of ART 1.17.0 introduces new adversarial training protocols, membership inference attacks, composite adversarial attacks for evasion and more.
Added
- Added Composite Adversarial Attack as evasion attack in PyTorch (#2287)
- Added support for black-box membership inference attacks without true labels (#2293)
- Added verbose option for progress bars in methods
fit
andpredict
of all classification estimators (#2334) - Added Oracle Aligned Adversarial Training (OAAT) in PyTorch (#2348)
Fixed
- Fixed bug in
ActivateDefense
andSpectralSignatures
poisoning defences by flattening the outputs when callingget_activations()
(#2327) - Fixed bug in Hugging Face classification estimator to correctly infer device if provided model is already on GPU (#2300)
Download && Tutorial
Copyright (C) IBM Corporation 2018