Machine learning tool to classify network packets.

FlowMeter is an open-source tool that analyses and classifies packet captures using machine learning techniques. It is an experimental project which is being used at Deepfence to evaluate how effectively one can train an ML model to discriminate between different types of traffic flows, e.g. normal and anomalous. You can build and install FlowMeter from GitHub: You can use sample data from various sources (see the README), or gather packet captures using PacketStreamer or other pcap tools. More information in the README, here: and this blogpost: Hope some people find it useful; we’d welcome any feedback, thank you.
Siddharth Satpathy

Machine learning scientist, researcher, astrophysicist.