Internet Video Quality Inference from Encrypted Network Traffic

Speaker : Francesco Bronzino
Nokia Bell Labs
Date: 16/01/2019
Time: 2:00 pm
Location: LINCS / EIT Digital


Accurately monitoring application performance is becoming more important for Internet Service Providers (ISPs), as users increasingly expect their networks to consistently deliver acceptable application quality. At the same time, the rise of end-to-end encryption makes it difficult for network operators to determine video stream quality — including metrics such as startup delay, resolution, rebuffering, and resolution changes –directly from the traffic stream. In this talk we present general methods to infer streaming video quality metrics from encrypted traffic using lightweight features. Our evaluation shows that our models are not only as accurate as previous approaches, but they also generalize across multiple popular video services, including Netflix, YouTube, Amazon Instant Video, and Twitch. The ability of our models to rely on lightweight features points to promising future possibilities for implementing such models at a variety of network locations along the end-to-end network path, from the edge to the core.
Stemming from the outcomes of this analysis, in the second part of the talk we present Network Microscope, a novel lightweight system running at the home getaway that analyzes traffic generated by DASH on-demand and live video streams. By first separating video flows from other sources of traffic by mapping DNS requests, the system tracks traffic patterns to infer key video quality metrics such as average bitrate and re-buffering events. Moreover, the system exploits novel algorithms that use simple probing techniques, i.e. lightweight pings and traceroutes, to take advantage of the home network vantage point to pinpoint where potential root causes hampering the streaming process might be located.


Francesco Bronzino is a Research Scientist in the Network Protocol and Systems Research department at Bell Labs Paris-Saclay. Francesco received his Ph.D. in Electrical and Computer Engineering from WINLAB (Wireless Information Network Lab) at Rutgers University, working on designing and developing name-based services for future Internet and mobile network architectures. For his thesis work he was awarded the “Graduate Program Academic Achievement Award” from the department. Before joining Bell Labs, Francesco spent two years as a Post-Doctoral research fellow in the MiMove group at Inria, Paris, where worked on developing network systems aimed at supporting and enhancing network services from home and access networks. Francesco’s research interests broadly focus on the Internet infrastructure and the services that populate it, with interest in understanding systems, protocols and new technologies that can enhance service development and performance.