Advanced Trustworthy AI - Preview Resilient AI: Defense from security & privacy attacks
You are currently viewing a preview of the course. If you already have course credentials, please sign up or log in.
Chapter 4

Resilient AI: Defense from security & privacy attacks

In this chapter, we’ll introduce the typical security and privacy attacks made on existing AI systems as well as their corresponding defense strategies. The aim is to understand some typical technical solutions to mitigate security and privacy attacks. Finally, through the presentation of industrial use cases, we show how these solutions are applied in practice.

SectionExercises
I. Attacks against machine learning systems
II. Technical solutions to mitigate attacks
III. Industry examples of privacy and security
About UsHelp CenterTerms & ConditionsPrivacy PolicyContact us

This course has been created with the SPATIAL project, brand name of an EU-funded project that tackles the identified gaps of data issues and black-box AI by designing and developing resilient accountable metrics, privacy-preserving methods, verification tools and system solutions that will serve as critical building blocks for trustworthy AI in ICT systems and cybersecurity.

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement N° 101021808. This communication reflects only the author’s view. It does not represent the view of the European Commission and the EC is not responsible for any use that may be made of the information it contains.