trusted AI

Making Neural Networks Robust with New Perspectives

IBM researchers have partnered with scientists from MIT, Northeastern University, Boston University and University of Minnesota to publish two papers on novel attacks and defenses for graph neural networks and on a new robust training algorithm called hierarchical random switching at IJCAI 2019.

Continue reading

Introducing AI Explainability 360

IBM Research AI announced AI Explainability 360, a comprehensive open-source toolkit of state-of-the-art algorithms that support the interpretability and explainability of machine learning models.

Continue reading

IBM Research Releases ‘Diversity in Faces’ Dataset to Advance Study of Fairness in Facial Recognition Systems

Originally published January 29, 2019; updated February 15, 2019, to reflect important contributions from Joy Buolamwini and Timnit Gebru in Gender Shades (2018) cited in the Diversity in Faces arXiv paper.

Continue reading

Building Ethically Aligned AI

IBM Research has studied and assessed two possible ways to solve AI's "value alignment" problem and build ethically aligned AI systems.

Continue reading

Trust and Transparency for AI on the IBM Cloud

A comprehensive new set of trust and transparency capabilities for AI on the IBM Cloud will support development of trusted AI services.

Continue reading

Introducing AI Fairness 360

IBM Research announces AI Fairness 360, a comprehensive open-source toolkit of metrics and algorithms to check for and mitigate unwanted bias in AI.

Continue reading

Factsheets for AI Services

Like nutrition labels for foods, factsheets for AI services would provide information about the product’s important characteristics.

Continue reading