TY - GEN
T1 - Beauty and the burst
AU - Schuster, Roei
AU - Shmatikov, Vitaly
AU - Tromer, Eran
N1 - Publisher Copyright:
© 2017 by The USENIX Association. All Rights Reserved.
PY - 2017
Y1 - 2017
N2 - The MPEG-DASH streaming video standard contains an information leak: even if the stream is encrypted, the segmentation prescribed by the standard causes content-dependent packet bursts. We show that many video streams are uniquely characterized by their burst patterns, and classifiers based on convolutional neural networks can accurately identify these patterns given very coarse network measurements. We demonstrate that this attack can be performed even by a Web attacker who does not directly observe the stream, e.g., a JavaScript ad confined in a Web browser on a nearby machine.
AB - The MPEG-DASH streaming video standard contains an information leak: even if the stream is encrypted, the segmentation prescribed by the standard causes content-dependent packet bursts. We show that many video streams are uniquely characterized by their burst patterns, and classifiers based on convolutional neural networks can accurately identify these patterns given very coarse network measurements. We demonstrate that this attack can be performed even by a Web attacker who does not directly observe the stream, e.g., a JavaScript ad confined in a Web browser on a nearby machine.
UR - http://www.scopus.com/inward/record.url?scp=85056206199&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85056206199
T3 - Proceedings of the 26th USENIX Security Symposium
SP - 1357
EP - 1374
BT - Proceedings of the 26th USENIX Security Symposium
PB - USENIX Association
Y2 - 16 August 2017 through 18 August 2017
ER -