The TAILOR Handbook of Trustworthy AI#

An encyclopedia of the major scientific and technical terms related to Trustworthy Artificial Intelligence

According the Ethics Guidelines for Trustworthy AI by High-Level Expert Group on Artificial Intelligence, Trustworthy Artificial Intelligence (Trustworthy AI) has three components, which should be met throughout the system’s entire life cycle. Indeed, it should be:

  1. lawful, complying with all applicable laws and regulations;

  2. ethical, ensuring adherence to ethical principles and values;

  3. robust, both from a technical and social perspective since, even with good intentions, AI systems can cause unintentional harm.

Executive Abstract#

The main goal of the Handbook of Trustworthy AI (HTAI) is to provide to non-experts, researchers and students, an overview of the problem related to the developing of ethical and trustworthy AI systems. In particular, the HTAI aims at providing an overview of the main dimensions of trustworthiness, starting with a understandable explanation of the dimension itself, and then presenting the characterization of the problems (starting with a brief summary and the explanation of the importance of the dimension, presenting a taxonomy and some guidelines, if they are available and consolidated), summarizing what are the major challenges and solutions in the field, and concluding with what are the latest research developments.

Each entry will be correlated with a bibliography, allowing the reader to go more in depth with a specific topic if interested knowing more about it.

All the entries have a list of authors that have directly contributed to the writing of the HTAI (some of them are already external to the TAILOR consortium), while the complete list of contributors can be found here.

About the TAILOR Handbook#

The HTAI assumes an encyclopedia-like structure and is presented in the form of a publicly accessible WIKI. To do so, the Jupiter Book framework has been used. In the long term, the Handbook is meant to become a point of reference for resources (key concepts, tools, documentation, tutorials, teaching material, etc.) related to Trustworthy AI.

Here, you can find the The Ethical and Legal Framework we are referring to, to have the context of the current European context.

The organization of the chapters is based on the seven principles described in the Ethics Guidelines for Trustworthy AI of the High-Level Expert Group on Artificial Intelligence [1]. In particular, in this Encyclopedia, you can find definitions related to:

  • Human Agency and Oversight. This section of the Encyclopedia defines Human agency, i.e., the necessity of knowledge and tools to comprehend and interact properly with AI systems, and Human oversight in different phases of AI processes.

  • Technical Robustness and Safety. In this section of the Encyclopedia, we analyze the challenges in developing AI systems that are safe, reliable, and robust; we also provide a way to evaluate these aspects in practice, and we promote the dynamic evaluation in managing risk during the normal use of AI systems.

  • Privacy and Data Governance. This section will focus mostly on the Respect for Privacy side. Here, we provide an overview of the main attacks that can threaten individual privacy, explain the difference between pseudonymization and actual anonymization, and describe the main family of privacy models.

  • Transparency. In this part of the Handbook, we will first provide the distinction between a transparent model and an explainable one (indeed, in the ML context, a commonly study problem is related to the Explainable AI). In this section, we provide an overview of the main properties that an explanation should have and of the several methods to provide multi-modal explanations; moreover, our focus will also be on overcoming the need to explain the opaque model and, instead, move toward the use of transparent models.

  • Accountability. Here, we analyze the two souls of this topic, the two interrelated concepts of Accountability and Reproducibility: the former term is more related to responsibility, blameworthiness, liability, and preventing misuse, while the latter term is more related to measures, quality standards, and procedures to model the development of learning methods for AI.

  • Diversity, Non-Discrimination, and Fairness. In this chapter, we will start recalling what the grounds of discrimination are, how we can define a bias or segregation; then, we will make a step in determining what fair machine learning could be, what are the metrics we can adopt to measure (un)fairness, and, more generally, how we could move towards Justice by Design systems.

  • Societal and Environmental Wellbeing. The last chapter of the Handbook is focus of one of the newest challenge that our society is facing. In particular, our focus is on environmental wellbeing (aka sustainability) and on providing solutions to optimize both the resources used in AI systems and the computation itself.

As one can see, we mapped one of the seven requirements for Trustworthy AI, as defined by the High-Level Expert Group on AI [1], in a chapter of this Handbook. However, there are some differences in emphasis, as the TAILOR project is more focused on specific aspects, e.g., more on privacy than on data governance, more on the sustainability of AI than on societal wellbeing, and more on post-hoc explanations than on transparency.

Finally, we report a final chapter, where you can find an Index that lists all entries in alphabetical order. In each term, you can find a reference to a short definition of the entry and where it is used within the Handbook, with a link to go more in-depth with the definition. Potential synonyms have their own entries in this index.



High-Level Expert Group on Artificial Intelligence. Ethics Guidelines for Trustworthy AI. URL: (visited on 2024-04-23).


Giovanni Comandé, editor. Elgar Encyclopedia of Law and Data Science. Edward Elgar Publishing, 2022. ISBN 978-1.83910-458-9. URL:


Juan Ramón Rabuñal Dopico, Julian Dorado, and Alejandro Pazos, editors. Encyclopedia of Artificial Intelligence (3 Volumes). IGI Global, 2008. ISBN 9781599048499. doi:10.4018/978-1-59904-849-9.


Claude Sammut and Geoffrey I. Webb, editors. Encyclopedia of Machine Learning and Data Mining. Springer, 2017. ISBN 978-1-4899-7685-7. URL:, doi:10.1007/978-1-4899-7687-1.


Aris Gkoulalas-Divanis and Claudio Bettini, editors. Handbook of Mobile Data Privacy. Springer, 2018. ISBN 978-3-319-98160-4. URL:, doi:10.1007/978-3-319-98161-1.

This entry was written by Francesca Pratesi and Umberto Straccia.

This research was partially supported by TAILOR, a project funded by EU Horizon 2020 research and innovation programme under GA No 952215