European Commission logo
English English
CORDIS - EU research results

Human-Compatible Artificial Intelligence with Guarantees

Project description

Exploring the ethical use of AI

Artificial intelligence powers a growing number of systems today. This is why it’s important to make sure the AI algorithms work correctly. In this context, the EU-funded AutoFair project will focus on the issue of fairness. Specifically, it will deal with the design of explainable and transparent AI algorithms. AutoFair aims to improve the algorithms themselves while educating end users. It draws on knowledge from computer and data sciences, control theory, optimisation and other scientific disciplines, including ethics and law. Three case studies will be carried out to test the findings on the automation of fair evaluation in recruitment, the elimination of gender inequality in advertising and the elimination of discrimination against bank clients.


In this proposal, we address the matter of transparency and explainability of AI using approaches inspired by control theory. Notably, we consider a comprehensive and flexible certification of properties of AI pipelines, certain closed-loops and more complicated interconnections. At one extreme, one could consider risk averse a priori guarantees via hard constraints on certain bias measures in the training process. At the other extreme, one could consider nuanced communication of the exact tradeoffs involved in AI pipeline choices and their effect on industrial and bias outcomes, post hoc. Both extremes offer little in terms of optimizing the pipeline and inflexibility in explaining the pipeline’s fairness-related qualities. Seeking the middle-ground, we suggest a priori certification of fairness-related qualities in AI pipelines via modular compositions of pre-processing, training, inference, and post-processing steps with certain properties. Furthermore, we present an extensive programme in explainability of fairness-related qualities. We seek to inform both the developer and the user thoroughly in regards to the possible algorithmic choices and their expected effects. Overall, this will effectively support the development of AI pipelines with guaranteed levels of performance, explained clearly. Three use cases (in Human Resources automation, Financial Technology, and Advertising) will be used to assess the effectiveness of our approaches.


Net EU contribution
€ 561 847,50
160 00 Praha

See on map

Česko Praha Hlavní město Praha
Activity type
Higher or Secondary Education Establishments
Total cost
€ 561 847,50

Participants (6)

Partners (1)