A Microservice Architecture for Online Mobile App Optimization

Zhao, Yixue; Medvidović, Nenad

doi:10.1109/mobilesoft.2019.00017

Cited by 3 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the traffic of an app captured at different times, it is challenging to identify a unique signature that can be used to classify the app. Last but not least, to optimize the performance, modern mobile apps are designed and developed using micro-services that share the same libraries and use content delivery networks (CDNs) and third-party services [50]. For such apps, using domain name resolution or IP address lookup for app classification may not be useful.…”

Section: Introductionmentioning

confidence: 99%

MAppGraph: Mobile-App Classification on Encrypted Network Traffic using Deep Graph Convolution Neural Networks

Pham

Truong-Huu

et al. 2021

Annual Computer Security Applications Conference

View full text Add to dashboard Cite

Identifying mobile apps based on network traffic has multiple benefits for security and network management. However, it is a challenging task due to multiple reasons. First, network traffic is encrypted using an end-to-end encryption mechanism to protect data privacy. Second, user behavior changes dynamically when using different functionalities of mobile apps. Third, it is hard to differentiate traffic behavior due to common shared libraries and content delivery within modern mobile apps. Existing techniques managed to address the encryption issue but not the others, thus achieving low detection/classification accuracy. In this paper, we present MApp-Graph, a novel technique to classify mobile apps, addressing all the above issues. Given a chunk of network traffic generated by a mobile app, MAppGraph constructs a communication graph whose nodes are defined by tuples of IP address and port of the services connected by the app, edges are established by the weighted communication correlation among the nodes. We extract information from packet headers without analyzing encrypted payload to form feature vectors of the nodes. We leverage deep graph convolution neural networks to learn the diverse communication behavior of mobile apps from a large number of graphs and achieve a fast classification. To validate our technique, we collect traffic of a hundred mobile apps on the Android platform and run extensive experiments with various experimental scenarios. The experimental results show that MAppGraph significantly improves classification accuracy by up to 20% in various metrics compared to recently developed techniques and demonstrates its practicality for security and network management for mobile services.

show abstract

Section: Introductionmentioning

confidence: 99%