Ben Edwards | Searcharxiv

arXiv2026

The UK and Ireland Geophysical Array -- Concept and Design

Scientific exploration of the UK and Ireland's subsurface has made important contributions to scholarship and prosperity for people and the planet, including economic growth, sustainable use of natural resources, storage of greenhouse gases, and inspiring curiosity about the Earth beneath our feet. This article outlines a vision for an array of seismological instruments spanning the UK and Ireland, UKI Array, augmented by other types of geophysical sensors, to maximise the value offered by existing equipment pools. The mission is to research natural phenomena and structure in the deep and shallow Earth, to solve problems concerning hazards and resources, to connect scientists to schools and the broader public, and thus to inspire a new generation to learn about geophysics. The vision was created through a community driven process of engagement and participation. This paper describes the concept and design of the UKI-Array; a companion paper discusses related opportunities and potential applications.

physics.geo-ph↗

arXiv2018

Adversarial Robustness Toolbox v1.0.0

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).

cs.LG↗