Adaptive network probing using machine learning

A computer-implemented method for scanning a computer network, comprising:

• a) sending, by a computer processor, a network probe to a particular port at a network address in a computer network;
• b) receiving, by the computer processor, a response to the network probe from the network address;
• c) appending, the computer processor, the response to a set of features forming a feature vector;
• d) determining, by the computer processor, a next port at the network address to probe;
• and
• e) predicting, by the computer processor, the response from the next port using the feature vector and a model, where the model is trained using a machine learning method and outputs a probability that a given port will respond to a network probe in a desired manner.

A computer-implemented method for predicting a response of a network probe in a computer network, comprising:

• receiving, by a computer processor, a data set representing a plurality of network probes in a computer network, where each entry in the data set includes a network address for a given network probe and an indicator of the response to the given network probe;
• determining, by the computer processor, a geographic location for the network address associated with each entry in the data set;
• constructing, by the computer processor, a series of feature vectors from the data set, where each feature vector includes a network address for a network probe, a geographic location for the network address and an indicator of the response given by the network address to a network probe;
• and
• training, by the computer processor, a model with a machine learning method using the series of feature vectors, where the model outputs a probability that a given network address will respond to a request in a desired manner.

A network scanner, comprising

• a processor;
• and
• a storage medium having computer program instructions stored thereon, when executed by the processor, perform to:
• sending, by a computer processor, a network probe to a network address in a computer network;
• receiving, by the computer processor, a response to the network probe from the network address;
• appending, the computer processor, the response to a set of features forming a feature vector;
• determining, by the computer processor, a next probe to conduct at the network address;
• and
• predicting, by the computer processor, the response from the next probe using the feature vector and a model, where the model is trained using a machine learning method and outputs a probability that a given network address will respond to a given network probe in a desired manner.