MAppPrint: Robust and Real-time Mobile App Fingerprinting via Traffic Behavior Correlation Graphs
MAppPrint fingerprints mobile apps from encrypted traffic using behavior graphs, including concurrent apps.
MAppPrint is a mobile app fingerprinting framework that builds Traffic Behavior Correlation Graphs from encrypted traffic, capturing unit behaviors and their correlations. Graph compression supports real-time use, and an unsupervised decomposition step separates mixed traffic from concurrent apps. Experiments report 4.9–13.9% higher precision and three to six times better timeliness than prior methods, with 10.5 GB/s throughput and 0.68-second prediction latency under dynamic network conditions.
- Traffic Behavior Correlation Graphs model app-specific encrypted traffic.
- Compression and unsupervised decomposition handle concurrent multi-app traffic.
- Precision rises 4.9–13.9% and timeliness improves three to six times.
- Reported throughput is 10.5 GB/s with 0.68-second prediction latency.
From the original article
1 min read at arxiv.orgMobile apps have become ubiquitous in daily life. Despite communication encryption, app fingerprinting (AF) attacks can still enable adversaries to infer the apps in use by analyzing patterns of encrypted network traffic.
By Tao Duan · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.