Nozomi Networks Sagl

Alessandro Zamberletti

Moreno Carullo

Alessandro Di Pinto

Alessandro Cavallaro Corti

Alessandro Valente

Luca Cremona

The present invention relates to a method for detecting anomalies in data traffic generated by peripheral devices simulating human-like patterns retrieving all data packets sent by a peripheral device to a computer, identifying a data communication as a plurality of the data packets in a predetermined timeframe, parsing the content of each of the data packets of the data communication to extract a plurality of communication features of the data communication, classifying the communication features through a set of absolute classifiers and through a set of majority classifiers and signalling an anomaly of the data communication when at least the majority in the set of absolute classifiers or at least one in the set of absolute classifiers define the data communication as malicious.

Method for detecting anomalies in data traffic generated by peripheral devices simulating human-like patterns

The present invention relates to a method for detecting anomalies in time series data produced by devices of an infrastructure in a network comprising, for each of the devices through computerized data processing means, retrieving a time series data for the device in the network, extracting a plurality of time series samples relating to respective time windows and having a predefined window size and a predefined stride, by sliding the time windows to overlap the time series data, supplying the time series samples as input to a Convolutional Autoencoder to define reconstructed time series values having a predefined percentile intervals, analysing the reconstructed time series values to identify anomalous behaviours of the time series data, signalling an anomaly of the device when at least one anomalous behaviour is identified.

Growing community of inventors

Luxembourg, Luxembourg

Alessandro Zamberletti