Predicting sex as a soft-biometrics from device interaction swipe gestures

Miguel-Hurtado, Oscar; Stevenage, Sarah V.; Bevan, Chris; Guest, Richard

doi:10.1016/j.patrec.2016.04.024

Cited by 35 publications

(30 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To explore the vulnerabilities exposed by the keystroke dynamics as a signature for mobility context detection, we recruited 13 volunteers (primarily college students who use different modes of transports daily during their travel from home to college and back) for the pilot study. The volunteers belong to the age group 18-35 (8-males and 5-females) which introduce sufficient diversity in the collected data [18]. We ask the volunteers to type texts over different Android apps which they regularly use and provide data 3 in different mobility contexts with one and two-handed modes of typing.…”

Section: A Typing Patterns For Tracking Mobility Contextmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Mobility Context over Smartphones using Typing and Smartphone Engagement Patterns

Chatterjee

Bhowmik

Singh

et al. 2020

2020 IEEE International Conference on Pervasive Computing and Communications (PerCom)

View full text Add to dashboard Cite

Most of the latest context-based applications capture the mobility of a user using Inertial Measurement Unit (IMU) sensors like accelerometer and gyroscope which do not need explicit user-permission for application access. Although these sensors provide highly accurate mobility context information, existing studies have shown that they can lead to undesirable leakage of location information. To evade this breach of location privacy, many of the state-of-the-art studies suggest to impose stringent restrictions over the usage of IMU sensors. However, in this paper, we show that typing and smartphone engagement patterns can act as an alternative modality to sniff the mobility context of a user, even if the IMU sensors are not sampled at all. We develop an adversarial framework, named ConType, which exploits the signatures exposed by typing and smartphone engagement patterns to track the mobility of a user. Rigorous experiments with in-the-wild dataset show that ConType can track the mobility contexts with an average micro-F 1 of 0.87 (±0.09), without using IMU data. Through additional experiments, we also show that ConType can track mobility stealthily with very low power and resource footprints, thus further aggravating the risk.

show abstract

Section: A Typing Patterns For Tracking Mobility Contextmentioning

confidence: 99%

“…Recent studies show that keystroke interaction patterns can detect the soft-biometric characteristics, such as age, handedness, etc. [18], [19] of a user. We leverage on those studies to explore the potential of inter-tap duration (ITD) to detect mobility contexts across different users.…”

Section: B Opportunitiesmentioning

confidence: 99%

Detecting Mobility Context over Smartphones using Typing and Smartphone Engagement Patterns

Chatterjee

Bhowmik

Singh

et al. 2020

2020 IEEE International Conference on Pervasive Computing and Communications (PerCom)

View full text Add to dashboard Cite

show abstract

“…The sensors in smartphones have been used to good effect to infer a wide range of information about an individual solely based on the way that they interact with the smartphone's touchscreen, for example inferring the length of the user's thumb [13] and as a result estimating their height or being used infer the user's gender [14]. They can also be used to infer the user's gait patterns [15], the activity being performed [16] even location and travel routes [17], [18].…”

Section: Introductionmentioning

confidence: 99%

Reconstructing What You Said: Text Inference Using Smartphone Motion

Hodges

Buckley

2019

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

Smartphones and tablets are becoming ubiquitous within our connected lives and as a result these devices are increasingly being used for more and more sensitive applications, such as banking. The security of the information within these sensitive applications is managed through a variety of different processes, all of which minimise the exposure of this sensitive information to other potentially malicious applications. This paper documents experiments with the 'zero-permission' motion sensors on the device as a side-channel for inferring the text typed into a sensitive application. These sensors are freely accessible without the phone user having to give permission. The research was able to, on average, identify nearly 30% of typed bigrams from unseen words, using a very small volume of training data, which was less than the size of a tweet. Given the natural redundancy in language this performance is often enough to understand the phrase being typed. We found that large devices were typically more vulnerable, as were users who held the device in one hand whilst typing with fingers. Of those bigrams which were not correctly identified over 60% of the errors involved the space bar and nearly half of the errors are within two keys on the keyboard.

show abstract

“…Characteristics like gender, age, ethnicity can provide information that helps to determine the identity. This type of biometric is labeled soft-biometrics [Miguel-Hurtado et al 2016]. Traditional systems that combine hard-biometrics (physical characteristics) within unimodal soft-biometrics can still suffer problems like nonuniversal biometrics traits, or insufficient accuracy caused by noisy data.…”

Section: Introductionmentioning

confidence: 99%

An evaluation of a three-modal hand-based database to forensic-based gender recognition

Abreu¹,

Goncalve²

2019

Anais Do XIX Simpósio Brasileiro De Segurança Da Informação E De Sistemas Computacionais (SBSeg 2019)

View full text Add to dashboard Cite

In recent years, behavioural soft-biometrics have been widely used to improve biometric systems performance. Information like gender, age and ethnicity can be obtained from more than one behavioural modality. In this paper, we propose a multimodal hand-based behavioural database for gender recognition. Thus, our goal in this paper is to evaluate the performance of the multimodal database. For this, the experiment was realised with 76 users and was collected keyboard dynamics, touchscreen dynamics and handwritten signature data. Our approach consists of compare two-modal and one-modal modalities of the biometric data with the multimodal database. Traditional and new classiﬁers were used and the statistical Kruskal-Wallis to analyse the accuracy of the databases. The results showed that the multimodal database outperforms the other databases.

show abstract

Predicting sex as a soft-biometrics from device interaction swipe gestures

Cited by 35 publications

References 11 publications

Detecting Mobility Context over Smartphones using Typing and Smartphone Engagement Patterns

Detecting Mobility Context over Smartphones using Typing and Smartphone Engagement Patterns

Reconstructing What You Said: Text Inference Using Smartphone Motion

An evaluation of a three-modal hand-based database to forensic-based gender recognition

Contact Info

Product

Resources

About