Author:
Tartu Ülikool

Abdul-Rasheed Ottun: explainability of AI is at the centre of my PhD research and SPATIAL agenda

Here is the editorial of Abdul-Rasheed Ottun from the SPATIAL PhD series. Abdul-Rasheed Ottun is a first-year PhD candidate and a Junior Research fellow of Pervasive Computing at the institute of computer science of the University of Tartu, Estonia. His PhD research is in the area of artificial intelligence (AI) and drone technology.

Today, Artificial Intelligence (AI) is integrated into drones to enable the autonomous operations of drones with little or no human intervention, causing increasing uptake in the deployment of autonomous drones for different operations such as delivery operations, search and rescue operations, pollution monitoring etc., which calls for the need to guarantee that their operations can be trustworthy.

Meaning that, to what extent can their operation be safe, resilient in the advent of the unexpected, and comprehensible to users? Since the explainable AI (XIA) methods have recently emerged as a mechanism that can help understand AI models’ behaviour and the factors affecting them, I intend to use XAI to improve accountability and resilience in drone technology in my research.

Explainability of AI is at the centre of my PhD research and SPATIAL agenda. It is the extent to which the behaviour (inner working) of an AI algorithm can be described to humans in any AI application.

I joined the SPATIAL project during the last quarter of 2021. In my opinion, it is a profound and ambitious project, as it seeks to ensure that AI-based solutions -especially in the cybersecurity domain – are resilient, accountable, trustworthy, transparent and explainable.

Given SPATIAL’s ambition and the increasing uptake of AI in society, the project has a high potential to impact different segments of society, such as regulation, business, technology, and education.

I feel highly privileged to be part of SPATIAL. The tasks and responsibilities I undertake and my teams’ expected contributions to SPATIAL are moulding my experience in scientific research and project management.  Being the only PhD student member on UT’s SPATIAL team, my responsibilities broadly relate to research, deliverables management, communications, work package tasks (activities) coordination, and other management aspects of SPATIAL.

So far, the journey has not been without its challenges. However, the challenges present various opportunities to acquire and build competencies and collaborate with leading scientists in solution development, capacity development, relationship building, and social and scientific network creation.

I am optimistic about SPATIALS’ objectives and hope that its findings and technological solutions are adopted for industrial usage”.

Researchers from the University of Tartu’s Institute of Computer Science are taking part in the EU Horizon project SPATIAL (Security and Privacy Accountable Technology Innovations, Algorithms and Machine Learning), which aims to develop 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. 

Image
Rasheed Ottun
Woman standing

Doctoral defence: Pille Pullonen-Raudvere “Foundations of efficient and secure algorithm development for secure multiparty computation“

Võitjate autasustamine

Best student projects in 2024 selected

Doktorant teeb laval ettekannet

Mark your calendars: three-minute thesis competition for doctoral students to be held on 2 October