Detecting homographs of domain names
AssigneeInfoblox Inc.
InventorFemi Olumofin
Life of this patent
Estimating the term…
Abstract
Various techniques for detecting homographs of domain names are disclosed. In some embodiments, a system, process, and/or computer program product for detecting homographs of domain names includes receiving a DNS data stream, wherein the DNS data stream includes a DNS query and a DNS response for resolution of the DNS query; applying a homograph detector for each domain in the DNS data stream; and detecting a homograph of a domain name in the DNS data stream using the homograph detector.
Claims15
A system, comprising:
- a processor configured to:
- generate training and test data sets for images of characters for domain names;
- train a homograph classifier using the training and test data sets to recognize Unicode characters that are visually similar to one or more ASCII characters, wherein a convolutional neural network (CNN) architecture is used to train the homograph classifier, wherein the CNN architecture learns a filter to detect a pattern for a prediction, and wherein a presence of the pattern or a lack of the pattern is used by the CNN architecture to make the prediction;
- and
- execute the homograph classifier over a set of Unicode characters to generate an ASCII to Unicode map;
- and
- a memory coupled to the processor and configured to provide the processor with instructions.
A method, comprising:
- generating, using a processor, training and test data sets for images of characters for domain names;
- training, using the processor, a homograph classifier using the training and test data sets to recognize Unicode characters that are visually similar to one or more ASCII characters, wherein a convolutional neural network (CNN) architecture is used to train the homograph classifier, wherein the CNN architecture learns a filter to detect a pattern for a prediction, and wherein a presence of the pattern or a lack of the pattern is used by the CNN architecture to make the prediction;
- and
- executing, using the processor, the homograph classifier over a set of Unicode characters to generate an ASCII to Unicode map.
A computer program product, the computer program product being embodied in a tangible non-transitory computer readable storage medium and comprising computer instructions for:
- generating training and test data sets for images of characters for domain names;
- training a homograph classifier using the training and test data sets to recognize Unicode characters that are visually similar to one or more ASCII characters, wherein a convolutional neural network (CNN) architecture is used to train the homograph classifier, wherein the CNN architecture learns a filter to detect a pattern for a prediction, and wherein a presence of the pattern or a lack of the pattern is used by the CNN architecture to make the prediction;
- and
- executing the homograph classifier over a set of Unicode characters to generate an ASCII to Unicode map.
Dependencies are inferred from the claim text.