Machine learning for encrypted traffic using restnet

This compares Rest Net vs MLP presented fro Show and Tell

1. Machine Learning for Encrypted Traffic Behavior Modelling Abdul Samadh and Madhusoodhana Chari S

2. Problem Statement: With the growing adoption of encrypted traffic, Encrypted Network Traffic Classification of different sorts has been very pivotal to network management, visibility and security. With scaling networks and network usage the continuous monitoring of networks has become very important. Solution: We observe the flow statistical properties from the packet header. We specifically propose using a residual network to treat statistical network data as images and perform classification.

3. Why RESNET? Solves the vanishing gradient problem in deep neural networks . Deeper neural networks are better at classifying highly complex data. Gives us a general classification framework with networking traffic modelling instead of using specific models for specific use cases. Ability to model complex non-linear relations and achieve more expressiveness and generalization. Better scalability

4. Features:

5. Transformation: 00000000 00000000 00000000 00101101 00000000 00000000 00000000 00000011 00000000 00000000 10010111 10100111 00000000 00000000 10101001 00000101 00000000 00000000 00000000 00000001 00000000 00000000 00000000 01001011

6. Confusion Matrix

7. Results: