Operationalising Trustworthy AI in Cybersecurity (Virtual)

About this event

This event takes place on our Cambridge campus. You can also join us in-person.

Join us for Professor Shareeful Islam's Inuaugral focusing on the role of AI in modern cybersecurity.

Artificial Intelligence (AI) is now foundational to modern cybersecurity, powering systems capable of detecting threats and responding proactively. As digital environments grow more complex and attackers become more sophisticated, the need for AI systems that are not only accurate but also trustworthy and resilient has never been greater.

This talk examines the critical shift from accuracy-focused AI to trustworthy AI (T‑AI)—systems that are transparent, explainable, privacy‑aware, and robust against adversarial attacks. These qualities are essential to meeting emerging regulatory standards such as the EU AI Act, which mandates stringent requirements around human oversight, data governance, and cybersecurity for high-risk AI systems.

Despite widespread adoption of AI‑driven security tools, recent incidents—such as prompt‑injection attacks on public chatbots, AI‑generated misinformation, and adversarial manipulation of machine learning classifiers—highlight ongoing vulnerabilities. Subtle alterations to data can trick models into misclassifying phishing attempts or misidentifying malicious files.

In this lecture, Professor Shareeful Islam introduces a structured Trustworthy AI pipeline designed to embed ethical, technical, and domain‑specific safeguards throughout the AI lifecycle. He will share outcomes from collaborations with industry and academic partners through two EU‑funded projects, illustrating how T‑AI principles can be operationalised to strengthen cybersecurity practice and support regulatory compliance.

About our speaker

Professor Shareeeful Islam is Professor of cybersecurity at Anglia Ruskin University. He is a leading researcher in cybersecurity with over 22 years of experience across teaching, project leadership, and academic research. He holds a visiting professorship at the LUT School of Engineering Sciences in Finland and has previously served as a visiting professor at the National Institute of Informatics (Japan) and a visiting researcher at SBA Research (Austria).

He has successfully secured approximately £800,000 in national and EU research funding and has supervised 13 PhD and MPhil students to completion. He currently leads two research projects funded by Horizon Europe and CHIST‑ERA. With more than 110 publications in top-tier journals and conferences, his research focuses on cybersecurity risk management, trustworthy AI, AI‑enabled cyber defence, and regulatory compliance.