Building AutoAI pipelines for cyber threat detection – IBM Developer

Join the Digital Developer Conference: AIOps & Integration to propel your AI-powered automation skills Register for free

Building AutoAI pipelines for cyber threat detection

Introductory lab session on applying AI (ML life cycle) for cyber security use cases. Its very typical during Threat hunting to determine whether activities are suspicious, and recommend its suspicious level. In this session users will learn how to use Watson Studio to train a ML model which does suspicious process classification. Using the data set provided, participants will run an Auto-AI pipeline selecting features that are important for the mode. A three category classification, that has labels like 0, 1 and 2 , indicating suspicious level is the outcome of the model. Participants will use Watson Studio to save and serve the ML model. Using a templated Python code to examine a STIX bundle, WML API is invoked to perform classification functions. Pre-req: Understanding of STIX, Python Environment: WatsonStudio, Jupyter Notebooks.