Project description
Experimentation playground to assess and repair bias on AI
Artificial intelligence (AI) is widely used in a large number of sectors due to the benefits of automation and optimisation. However, AI can be also a source of bias and discrimination that needs to be controlled, measured and avoided. In addition, there is a lack of knowledge on repairing and assessing bias in existing AI systems and on designing new bias-free AI tools. The EU-funded AEQUITAS project will change this by developing a controlled experimentation environment to help AI producers to increase awareness of bias produced by AI systems and evaluate and (possibly) repair existing AI systems. It will also provide guidelines for fair-by-design AI systems and raise awareness about risks from AI if not adequately handled and managed.
Objective
AI-based decision support systems are increasingly deployed in industry, in the public and private sectors, and in policy-making. As our society is facing a dramatic increase in inequalities and intersectional discrimination, we need to prevent AI systems to amplify this phenomenon but rather mitigate it. To trust these systems, domain experts and stakeholders need to trust the decisions.
Fairness stands as one of the main principles of Trustworthy AI promoted at EU level. How these principles, in particular fairness, translate into technical, functional social, and lawful requirements in the AI system design is still an open question. Similarly we don’t know how to test if a system is compliant with these principles and repair it in case it is not.
AEQUITAS proposes the design of a controlled experimentation environment for developers and users to create controlled experiments for
- assessing the bias in AI systems, e.g. identifying potential causes of bias in data, algorithms, and interpretation of results,
- providing, when possible, effective methods and engineering guidelines to repair, remove, and mitigate bias,
- provide fairness-by-design guidelines, methodologies, and software engineering techniques to design new bias-free systems
The experimentation environment generates synthetic data sets with different features influencing fairness for a test in laboratories. Real use cases in health care, human resources and social disadvantaged group challenges further test the experimentation platform showcasing the effectiveness of the solution proposed. The experimentation playground will be integrated on the AI-on-demand platform to boost its uptake, but a stand-alone release will enable on-premise privacy-preserving test of AI-systems fairness.
AEQUITAS relies on a strong consortium featuring AI experts, domain experts in the use case sectors as well as social scientists and associations defending rights of minorities and discriminated groups.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. This project's classification has been validated by the project's team.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. This project's classification has been validated by the project's team.
Keywords
Programme(s)
Funding Scheme
HORIZON-RIA - HORIZON Research and Innovation ActionsCoordinator
40126 Bologna
Italy