Collected research

Beauty and the Burst: Remote Identification of Encrypted Video Streams

Roei Schuster, Vitali Shmatikov, Eran Tromer · beautyburst.github.io

Variable bitrate encoding makes an MPEG-DASH stream's pattern of traffic bursts a fingerprint of the video's content, surviving encryption. A convolutional network trained on those patterns identifies which Netflix or YouTube title a user is watching, either passively on-path or remotely from JavaScript that floods the link and measures congestion, including against a different device on the same network.

Record

Researcher

Roei Schuster, Vitali Shmatikov, Eran Tromer

Published by

beautyburst.github.io

Topic

Other

In the archive

• Collected in the 2016–17 research round

Tags

• side-channel
• timing-attack
• info-leak
• javascript

This page is the archive's own catalogue record. The research is the work of Roei Schuster, Vitali Shmatikov, Eran Tromer, first published at the original source. Preserved copies are kept so the citation survives its host; this one was last captured on 10 August 2026.