Cybersecurity #ai#security
AI Security Agent for University ACMIS Achieves 0.966 Detection F1 with Sub-Millisecond Response
A research paper presents an AI-based security agent for university Academic Management Information Systems (ACMIS) that detects brute-force attacks, payment fraud, privilege escalation, and insider data theft. The agent, combining supervised anomaly detection, behavioural analytics, and a password recovery chatbot, achieved a macro-average F1 of 0.966 on a simulated dataset, with critical-tier response latency under 1 millisecond.
Jun 17, 2026 1 source