Internet of Things anomaly detection system based on joint learning and automatic encoder

The invention discloses an Internet of Things anomaly detection system based on joint learning and an automatic encoder, which relates to the field of Internet of Things security and comprises a data collection module, a data processing and selection module, a sub-detection module, a joint learning module and an anomaly detection module. The data collection module obtains the transmit-receive traffic of all Internet of Things devices in a local area network segment, and stores the transmit-receive traffic as pcap data. The data processing and selecting module receives the pcap data, selects 15 characteristics as data representatives, and stores the data representatives as JSON files; the sub-detection module uses a machine learning technology to obtain low-dimensional features represented by the data and is responsible for uploading a learning model; the joint learning module receives the learning model, stores the learning model after integration, and returns the learning model to each sub-detection module;