MACHINE LEARNING-BASED NETWORK DEVICE PROFILING

A method includes applying, by a computer, supervised machine learning to classify a network device that is associated with a security event occurring in a computer system based on data representing features of the network device. The security event is associated with a potential security threat to the computer system, and the classification of the network device by the supervised machine learning is associated with a confidence. The technique includes, in response to the confidence being below a threshold, applying an active machine learning classifier to the data to learn a classification for the data and using the classification learned by the active machine learning classifier to adapt the supervised machine learning to recognize the classification.