A Holistic Approach for Locating Traffic Differentiation in the Internet

The worldwide debate over Network Neutrality (NN) has been raging on for nearly two decades. According to NN principles, all traffic in the Internet must be treated with impartiality. In particular, unfair Traffic Differentiation (TD) is not allowed. Several strategies have been proposed for detecting TD, but locating the source of TD is still an under-explored topic. In this work, we present a holistic approach for unifying TD detection solutions into a single framework with the purpose of locating the source of TD. We propose an algorithm for combining measurements from multiple vantage points, and a strategy for selecting good vantage points. Our proposals leverage Internet peering properties to infer the behavior of individual Autonomous Systems (ASes), without requiring knowledge of the exact routes traversed by measurement probes. To evaluate our proposals, we first ran several experiments to confirm that indeed Internet routes do present the required properties. Then, several simulations were performed to assess the efficiency of our proposals. Results show that our approach is capable of locating TD under several different conditions. Another finding is that issuing measurements from a few end-hosts of core Internet ASes achieves similar results than from a much larger number of end-hosts at the edge.