Age group detection using smartphone motion sensors

Abstract

Abstract-Side-channel attacks revealing the sensitive user data through the motion sensors (such as accelerometer, gyroscope, and orientation sensors) emerged as a new trend in the smartphone security. In this respect, recent studies have examined feasibility of inferring user's tap input by utilizing the motion sensor readings and propounded that some user secrets can be deduced by adopting the different side-channel attacks. More precisely, in this kind of attacks, a malware processes outputs of these sensors to exfiltrate victims private information such as PINs, passwords or unlock patterns. In this paper, we describe a new side-channel attack on smartphones that aims to predict the age interval of the user. Unlike the previous works, our attack does not directly deal with recovering a target user's some secret, rather its sole purpose is determining whether she is a child or an adult. The main idea behind our study relies on the key observation that the characteristics of children and adults differ in hand holding and touching the smartphones. Consequently, we show that there is an apparent correlation between the motion sensor readings and these characteristics that build up our attack strategy. In order to exhibit efficiency of the proposed attack, we have developed an Android application named as BalloonLogger that evaluates accelerometer sensor data and perform child/adult detection with a success rate of 92.5%. To the best of our knowledge, in this work, for the first time, we point out such a security breach.

Kid on the phone! Toward automatic detection of children on mobile devices

“…When combining multiple gestures, we achieved similar accuracy compared to [56] and slightly better than [28] (for both younger and older children groups). In the sensor-based, our approach achieved much better performance when using a single sensor window as well as a combination of multiple ones compared to [9]. These results confirm the effectiveness of the proposed approaches.…”

“…The inclusion of a broad range of children' age may harm the classification performance as older children may have significantly different behavior compared to that of younger children. We further divided children subjects into two groups: young children (3)(4)(5)(6)(7)(8) and older children (9)(10)(11)(12). We then ran evaluation on data of these two groups combined with adults data using 10-fold cross validation.…”

Privacy implications of accelerometer data

“…Menz, Lord and Fitzpatrick compared gait features between young and elder subjects using acceleration signals and discovered that younger subjects showed greater step length, higher velocity and smaller step timing variability [68]. Using data from accelerometers in smartphones, Davarci et al were able to predict the age interval of test subjects with a success rate of 92.5% [69]. Their work is based on the observation that children and adults differ in the way they hold and touch smartphones.…”

Wearable Sensor-Based Gait Analysis for Age and Gender Estimation

“…Automated healthcare-whether sensor-based or vision-based-have become essential for the future [2][3][4][5][6]. Wearable devices are extensively explored in various applications of healthcare and elderly support [7][8][9]. There are ample of opportunities to explore various wearable sensors in the domain of activities of daily living (ADL), gait analysis, exercise, heart rate monitoring, respiration rate, and other vital information analysis.…”

“…Understanding age or gender has other applications in various fields. However, estimations of age and gender are not much explored using wearable sensors [9,15]. The existing approaches are limited to small datasets and with limited scopes.…”