Home

TIE is a project for application identification through network traffic analysis (aka Traffic Classification, Traffic Identification, etc.).

We aim at building a common platform for the study and the development of traffic classification techniques by fostering collaboration among researchers and practitioners.

TIE offers an open-source platform working as a multiple classifier system able to combine multiple classification techniques (implemented as separate plugins) and adopting different strategies of decision combination.

You can find more info about TIE in the documentation pages (see links on the left) and you can read a technical report about TIE in the publications section.

• multiple classification techniques can be run at the same time and combined
• designed to work also with live traffic (realtime and cyclic modes)
• opensource, large community participation, geared towards data/tools sharing
  • developer's documentation and fully functional examples
  • classification plugins API
  • easy to add extraction of new classification features
  • easy to add new decision combination strategies
  • easy to provide ground-truth along with anonymized traces
• graph & web report generation
• runs on Linux, FreeBSD, and MacOS X

TIE is the traffic classification engine at the basis of the SmarTIE platform, released by NM2