• A Charles Sturt University cyber expert has warned of the increasing threat of ransomware in digital ecosystems and emphasised the urgent need for intelligent, adaptive detection methods
• He showcased cutting-edge research for detecting and responding to ransomware threats in near real time
• He also introduced research on a new performance metric which evaluates the balance between detection accuracy and system throughput, one of the most pressing cybersecurity challenges today

A Charles Sturt University cyber researcher with a leading role at a recent international conference advocated for the development and adoption of improved cyber protections.

Associate Professor in Computing Rafiqul Islam (pictured above, right), a cybersecurity researcher and the leader of the Cybersecurity Research Group in the Charles Sturt School of Computing, Mathematics and Engineering, delivered a keynote address at the TIME 2025 Workshop at the ACM Web Conference 2025 in Sydney.

Since the invention of the World Wide Web in 1989, this conference (formerly known as the International World Wide Web Conference) is an annual in-person international academic conference about the future direction of the World Wide Web. It is the premier venue to present and discuss progress in research, development, standards and applications of the topics related to the Web.

Professor Islam was a keynote speaker, a discussion panellist and Chair of the Award Ceremony.

“I highlighted to my audience of computing and cyber experts the increasing threat of ransomware in digital ecosystems, emphasising the urgent need for intelligent, adaptive detection methods,” Professor Islam said.

“In my keynote address, ‘Advancing Cybersecurity’ (see Media Note at the end for technical details), I highlighted critical challenges and strategies in securing digital ecosystems and showcased cutting-edge research on detecting and responding to ransomware threats in real time.

“I introduced a novel detection framework that marks a significant advancement over existing detection models.”

Professor Islam said this design improves classification efficiency and processing speed, making the system highly suitable for near-real-time ransomware detection.

“The framework also features a continuous learning mechanism, allowing it to adapt to emerging ransomware strains through incremental mini-batch updates,” he said.

“This capability is critical in maintaining detection accuracy in the face of evolving cyber threats.”

Professor Islam also introduced a new performance metric ─ Weighted Efficiency Score (WES) ─ which evaluates the balance between detection accuracy and system throughput, offering a more holistic assessment of cybersecurity solutions.

“This research addresses one of the most pressing cybersecurity challenges today,” Professor Islam said. “Our framework not only improves detection rates but also enhances adaptability and efficiency, which are key to defending against sophisticated ransomware attacks.”

The research project is funded by the Cyber Security Cooperative Research Centre (CSCRC) and forms part of Charles Sturt University’s broader commitment to research excellence and innovation in cybersecurity.

“The work has been well received by academic and industry stakeholders and reinforces the University’s leadership in applied, real-world cybersecurity research,” Professor Islam said.

As a panellist for the conference discussion on ‘Bridging Innovation and Responsibility in Web Technologies’, Professor Islam contributed to the timely and valuable insights into human-in-the-loop AI, ethical challenges and pathways to responsible innovation in web technologies.

Professor Islam emphasised the importance of integrating ethical considerations and adaptive safeguards in AI-driven systems.

The prestigious ACM Web Conference 2025 was held at the International Convention Center in Sydney from Monday 28 April to Friday 2 May.