Man-in-the-Middle Attacks to Detect and Identify Services in Encrypted Network Flows using Machine Learning

Wireless access points are deployed rapidly as users demand to grow massively to meet sufficient quality of services. Recently, the need for internet utility is enormously rising as the era of streaming social media services highly entailed which are the utmost treasured for the users. However, these applications are classified as encrypted network traffic mainly to protect and to adhere to users' privacy. On the other hand, Machine Learning (ML) adopted in a wide range of data classification as an efficient approach to organize indistinct data. The ML algorithms are accommodating any type of information which can be structured or unstructured data to distinguish rational patterns that can result in an understanding of superior decisions and forecasts. Therefore, in this work, we elaborate on a lab experiment of the Man-in-the-Middle (MITM) attack which sniffs the encrypted network traffic and analyzes it in rich details through a supervised ML approach to classify the social media applications.