The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
InfoResearchPeer-reviewed
RDSAD: Robust Threat Detection in Evolving Data Streams via Adaptive Latent Dynamics
- Published
- Record updated
Summary
RDSAD is an unsupervised, adaptive anomaly-based intrusion detection method for evolving cyber-physical system (CPS) data streams. It combines Dynamic Deviation Recognition (DDR), which captures underlying system dynamics, with Shift-aware Model Adaptation (SMA), which updates the model as patterns change. It reached the best AUC of 0.90 on SWaT and 0.88 on WADI, outperforming static and streaming baselines with efficient runtime on large streams.