Research project title

Adversarial AI

Education level

Master or doctorate

Director/co-director

Director: Ranwa Al-Mallah

End of display

July 30, 2027

Areas of expertise

Cybersecurity

Primary sphere of excellence in research

New Frontiers in Information and Communication Technologies

Secondary sphere(s) of excellence in research

Modeling and Artificial Intelligence

Unit(s) and department(s)

Department of Computer Engineering and Software Engineering

Detailed description

Components of cyber physical systems, which affect real-world processes, are often exposed to the internet. Replacing conventional control methods with Artificial Neural Networks (ANN) in many cyber physical systems is an active area of research. However, ANNs are vulnerable to specific perturbations of their inputs: This project aims at modelling sophisticated AI-based cyberattacks targeting the infrastructure to disrupt the control discipline. By understanding the attacks and exposing the vulnerabilities, designing a process to create a new class of defensive cybersecurity solutions that are domain-specific and that take into account the control objectives of the defended system and the models of the physical world.

Financing possibility

I offer funding according to the MAFS ($22,500/year for the master's degree; $26,000/year for the doctorate).