MLEP in KICS 5.0 refines OT device categories with spiking neural networks
Original title: MLEP in KICS for Networks 5.0: how machine learning helps track network behavior of OT devices
MLEP processes 15-second network fragments using neurosemantic networks to detect anomalies when asset inventories are incomplete.
Kaspersky Industrial CyberSecurity for Networks 5.0 includes the Machine Learning Event Processor to analyze device network behavior patterns. It represents sessions as timestamped events of endpoints, protocols, and packet counts. The system learns typical interactions per device to classify unknown categories and spot deviations in OT environments where direct information is lacking.
- MLEP builds behavioral history from 15-second event fragments
- Uses spiking neural semantic networks with neurogenesis for new patterns
- Refines categories when hardware info from protocols or polling is incomplete
- Aggregates data but cannot reconstruct individual packets or command content
- CISA 2025 guidance highlights inventory and role classification as key OT priorities
From the original article
11 min read at securelist.com
We explain how Kaspersky Industrial CyberSecurity for Networks uses Machine Learning Event Processor (MLEP) technology to help take inventory of assets and detect anomalies in industrial networks.
By Roman Ezhov, Andrey Lavrentyev · securelist.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.