Method and system for identifying an application type of encrypted traffic
AssigneeNeuralitc Systems
InventorsMarc TREMBLAY, Sousso KELOUWANI, Eric MELIN
Life of this patent
Estimating the term…
Abstract
The present relates to a method and a system for identifying an application type from encrypted traffic transported over an IP network. The method and system extract at least a portion of IP flow parameters from the encrypted traffic using at least one of specific target encryption types. Then, the method and system transmit the extracted IP flow parameters to a learning-based classification engine. The learning-based classification engine has been trained with unencrypted traffic. Then, the method and system infer at least one corresponding application type for the extracted IP flow parameters.
Claims13
A method for identifying an application type from encrypted traffic transported over an IP network, the method comprising:
- extracting at least a portion of IP flow parameters from the encrypted traffic using at least one of specific target encryption types;
- transmitting the extracted IP flow parameters to a learning-based classification engine, the learning-based classification engine having been trained with unencrypted traffic;
- and
- inferring by the learning-based classification engine at least one corresponding application type for the extracted IP flow parameters.
A system for identifying an application type from encrypted traffic transported over an IP network, the system comprising:
- a classification engine for extracting IP flows from the encrypted traffic, and for identifying IP flows using at least one of specific target encryption types;
- a pre-processing unit for extracting IP flow parameters from the extracted IP flows using the at least one specific target encryption types;
- and
- a learning-based classification engine trained with unencrypted traffic, the learning-based classification engine inferring an application type for the extracted IP flows based on the extracted IP flow parameters.
Dependencies are inferred from the claim text.