AI RESEARCH
CALIBURN: A Regime-Sensitivity Study of Operationally Calibrated Streaming Intrusion Detection
arXiv CS.LG
•
ArXi:2605.24696v1 Announce Type: cross Streaming network intrusion detection systems must process flows continuously while keeping memory bounded, but most current methods leave alerting threshold selection as a post-hoc tuning problem poorly suited to production. Operators need alerting behaviour specifiable before deployment using inputs such as false-negative cost, false-positive cost, and alerting budget.