Giovanni Apruzzese

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 Survey of Knowledge (SoK) identifies a disconnect between academic NIDS research and real-world operational contexts, proposing foundational changes to reshape future research.

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 paper demonstrates that visual phishing detectors can be completely bypassed by employing simple timing-based attacks that delay the rendering of key webpage elements.

The paper introduces the concept of 'host-space perturbations,' arguing that real-world attackers can only manipulate network inputs by controlling specific hosts, a constraint that significantly weakens the security assumptions of current ML-NIDS research.