Irdin Pekaric

This paper investigates the practical barriers preventing the trustworthy deployment of AI-driven Cyber Threat Intelligence (CTI) in the highly regulated financial sector, identifying four key socio-technical failure modes.

The paper introduces SAFT-GT, a comprehensive model-based toolchain designed to simultaneously analyze and enhance both the safety and security of complex, self-adaptive systems.

This paper addresses the lack of specialized NLP tools for detecting toxicity in real-time video game chat by creating a large, fine-grained dataset and developing a superior, domain-specific detector.

This study investigated whether Security Operations Center (SOC) analysts can justify their decisions when triaging alarms, finding that while they are often correct in identifying true threats, they struggle significantly to provide accurate, evidence-based justifications.

This study provides a longitudinal analysis of dark web content, revealing that cybercrime discussions are dominated by a few persistent core topics rather than rapidly shifting themes.