TrCMP: An App Usage Inference Method for Mobile Service Enhancement

Zhao, Xuan; Bhuiyan, Zakirul Alam; Qi, Lianyong; Nie, Hongli; Rafique, Wajid; Dou, Wanchun

doi:10.1007/978-3-030-05345-1_19

Cited by 1 publication

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various methods have been leveraged, for instance, power usage [5], system behavior [6], and network traffic [7,8]. In [5,6], the authors developed malicious Android Apps to collect system information, such as current, voltage, network state, CPU and memory usage, from a victim's device. The collected data were analyzed and machine learning techniques were used to identify the Apps on the victim's device.…”

Section: App Fingerprintingmentioning

confidence: 99%

See 1 more Smart Citation

DeepMag+: Sniffing mobile apps in magnetic field through deep learning

Ning

Xin

Jiang

et al. 2020

Pervasive and Mobile Computing

View full text Add to dashboard Cite

This paper reports a new side-channel attack to smartphones using the unrestricted magnetic sensor data. We demonstrate that attackers can effectively infer the Apps being used on a smartphone with an accuracy of over 80%, through training a deep Convolutional Neural Networks (CNN). Various signal processing strategies have been studied for feature extractions, including a tempogram based scheme. Moreover, by further exploiting the unrestricted motion sensor to cluster magnetometer data, the sniffing accuracy can increase to as high as 98%. To mitigate such attacks, we propose a noise injection scheme that can effectively reduce the App sniffing accuracy to only 15% and at the same time has a negligible effect on benign Apps.

show abstract

Section: App Fingerprintingmentioning

confidence: 99%

“…Compared with their approaches, our work does not require to maliciously deploy an additional App [5,6] or a traffic sniff device [7,8] to collect data on the victim's device. Therefore, our approach can launch the sniffing attack easily by incentivizing users to visit our website.…”

Section: App Fingerprintingmentioning

confidence: 99%