In order to improve mobile data transparency, various approaches have been proposed to inspect network traffic generated by mobile devices and detect exposure of personally identifiable information (PII), ad requests, etc. State-of-the-art approaches use features extracted from HTTP packets and train classifiers in a centralized way: users collect and label network packets on their mobile devices, then upload data to a central server; the server uses the data contributed by all users to train a packet classifier. However, training datasets from network traffic collected on user devices may contain sensitive information that users may not want to upload. In this article, we propose a federated learning approach to mobile packet classification, which enables devices to collaboratively train a global model, without uploading the training data collected on devices. We apply our framework to two packet classification tasks (i.e., to predict PII exposure or ad requests in individual packets) and we demonstrate its effectiveness in terms of classification performance, communication and computation cost, using three real-world datasets. Methodological challenges we address in the process include model and feature selection, as well as tuning the federated learning parameters specifically for our packet classification tasks. We also discuss privacy limitations and mitigation approaches.

In this paper, we study the problem of generating synthetic graphs that resemble real-world graphs in terms of their degree correlations and potentially additional properties. We present an algorithmic framework that generates simple undirected graphs with the exact target joint degree matrix, which we refer to as 2K graphs, in linear time in the number of edges. Our framework imposes minimal constraints on the graph structure, which allows us to target additional graph properties during construction, namely, node attributes (2K+A), clustering (both average clustering, 2.25K, and degree-dependent clustering, 2.5K), and number of connected components (2K+CC). We also define, for the first time, the problem of directed 2K graph construction, provide necessary and sufficient conditions for realizability, and develop efficient construction algorithms. We evaluate our approach by creating synthetic graphs that target real-world graphs both undirected (such as Facebook) and directed (such as Twitter), and we show that it brings significant benefits, in terms of accuracy and running time, compared to the state-of-the-art approaches.

We study the problem of generating synthetic graphs that resemble real-world directed graphs in terms of their degree correlations. In order to capture degree correlation specifically for directed graphs, we define directed 2K (D2K) as those graphs with a given directed degree sequence (DDS) and a given target joint degree and attribute matrix (JDAM). We provide necessary and sufficient conditions for a target D2K to be realizable and we design an efficient algorithm that generates graph realizations with exactly the target D2K. We apply our algorithm to generate synthetic graphs that target real-world directed graphs (such as Twitter), and we demonstrate its benefits compared to state-of-the-art construction algorithms.

In networking research, it is often desirable to generate synthetic graphs with certain properties. In this paper, we present a new algorithm, 2K_Simple, for exact construction of simple graphs with a target joint degree matrix (JDM). We prove that the algorithm constructs exactly the target JDM and that its running time is linear in the number of edges. Furthermore, we show that the algorithm poses less constraints on the graph structure than previous state-of-the-art construction algorithms. We exploit this flexibility to extend 2K_Simple and design two algorithms that achieve additional network properties on top of the exact target JDM. In particular, 2K_Simple_Clustering produces simple graphs with a target JDM and average clustering coefficient close to a target, while 2K_Simple_Attributes produces exactly simple graphs with a target JDM and joint occurrence of node attribute pairs. We exhaustively evaluate our algorithms through simulation for small graphs, and we also demonstrate their benefits in generating graphs that resemble real-world social networks in terms of accuracy and speed; we reduce the running time by orders of magnitudes compared to previous approaches that rely on Monte Carlo Markov Chains.