Figure - available from: Security and Communication Networks
This content is subject to copyright. Terms and conditions apply.
Schematic graph of two adjacent touch events. (a) Time relationship between two adjacent touch events; (b) spatial relationship between two adjacent touch events.
Source publication
Recently, mobile technology has become closely linked with our daily activities. Smartphones are used for multiple personal tasks involving private information, such as communication, healthcare, and banking. Therefore, there is a high demand for user-friendly authentication methods that prevent unauthorized access to sensitive information. This pa...
Citations
... k-NN offers simplicity and speed without assumptions about data (e.g., distribution of the data) [44], while SVM excels in classification by finding an optimal separating hyperplane, even by using kernels like the radial basis function (RBF). SVM functions by mapping data to a high-dimensional feature space and has been applied to classification within the field of biometric authentication [33,[46][47][48]. k-NN has also been largely applied to biometric authentication [31,[49][50][51][52][53], given its strength in the classification of data where the distribution is not normally distributed [44]. ...
Mobile devices (e.g., tablets and smartphones) have been rapidly integrated into the lives of children and have impacted how children engage with digital media. The portability of these devices allows for sporadic, on-demand interaction, reducing the accuracy of self-report estimates of mobile device use. Passive sensing applications objectively monitor time spent on a given device but are unable to identify who is using the device, a significant limitation in child screen time research. Behavioral biometric authentication, using embedded mobile device sensors to continuously authenticate users, could be applied to address this limitation. This study examined the preliminary accuracy of machine learning models trained on iPad sensor data to identify the unique user of the device in a sample of children ages 6 to 11. Data was collected opportunistically from nine participants (8.2 ± 1.75 years, 5 female) in the sedentary portion of two semistructured physical activity protocols. SensorLog was downloaded onto study iPads and collected data from the accelerometer, gyroscope, and magnetometer sensors while the participant interacted with the iPad. Five machine learning models, logistic regression (LR), support vector machine, neural net (NN), k-nearest neighbors (k-NN), and random forest (RF), were trained using 57 features generated from the sensor output to perform multiclass classification. A train-test split of 80%–20% was used for model fitting. Model performance was evaluated using F1 score, accuracy, precision, and recall. Model performance was high, with F1 scores ranging from 0.75 to 0.94. RF and k-NN had the highest performance across metrics, with F1 scores of 0.94 for both models. This study highlights the potential of using existing mobile device sensors to continuously identify the user of a device in the context of screen time measurement. Future research should explore the performance of this technology in larger samples of children and in free-living environments.
... Alani [54] surveyed 4027 Android users worldwide to explore their privacy and security awareness and the results showed that the relevant safety awareness is in urgent need to be improved. For the purpose of making user-authentication of smart phone more friendly and safe, Wang et al. [55] proposed an innovative feature representation tactic for continuous authentication. They also conducted experiment on 180 participants and proved the efficiency and accuracy of the tactic. ...
Smart Connected Product(SCP) and Smart Environment(SE), typical product-service integrated system under intelligent manufacturing context, have attracted significant attentions from both researchers and practitioners owning to its effectiveness in enabling user interaction and improving user satisfaction. In this paper, we conduct a systematical literature review to summarize the current user-oriented SCP or SE researches. A totally 102 journal articles are fully analyzed to illustrate the current research concentration and highlight future research directions. Different from existing review articles that focus on specific SCP or SE, our research incorporates diverse SCPs or SEs and proposes an objective-based taxonomy, which distinguishes three objective dimensions, that is, integrated optimization within system, vertically iterative optimization of the system and the horizontally collaborative optimization between systems. Besides, we distill five user-oriented indictors, that is, user need identification, user interaction optimization, serve special group, user security protection as well as energy consumption improvement and combine them with three research objectives to unveil the mainstream research concentration. Finally, we summarize the research gap of existing works and propose seven future research directions for scholars and practitioners.
... Emerging smartphone commerce applications and services require secure access to sensitive and private data to function properly [1]- [5]. Smartphone device security is typically set using a password, PIN codes, pattern lock, and tokens to provide authorized users access to such data and services [6]- [8]. Moreover, users can quickly buy products and services through their mobile devices while conducting financial activities and making online purchases (such as mobile payments and mHealth) [9]. ...
... Deep learning algorithms have been used to make classification decisions for many touch-based mobile authentication models. For studies [7][8][9], CNN architectures were used for classification. In [7], researchers used their proposed feature representation tactic, multiple channels biological graph (MCBG), with CNN to enhance their continuous mobile authentication scheme. ...
... For studies [7][8][9], CNN architectures were used for classification. In [7], researchers used their proposed feature representation tactic, multiple channels biological graph (MCBG), with CNN to enhance their continuous mobile authentication scheme. MCBG takes touch and motion sensor data patterns and visualizes them into one of three feature graphs. ...
... Often, these data are difficult to process for authentication. While some studies such as [7,8,35,65] account for this variability in their data collection and preprocessing stages and allow unconstrained data collection and realistic smartphone usage, many studies instruct their volunteers to follow more rigid instructions for data collection and testing. This can result in models that are not equipped to handle authentication in real-life scenarios. ...
Throughout the past several decades, mobile devices have evolved in capability and popularity at growing rates while improvement in security has fallen behind. As smartphones now hold mass quantities of sensitive information from millions of people around the world, addressing this gap in security is crucial. Recently, researchers have experimented with behavioral and physiological biometrics-based authentication to improve mobile device security. Continuing the previous work in this field, this study identifies popular dynamics in behavioral and physiological smartphone authentication and aims to provide a comprehensive review of their performance with various deep learning and machine learning algorithms. We found that utilizing hybrid schemes with deep learning features and deep learning/machine learning classification can improve authentication performance. Throughout this paper, the benefits, limitations, and recommendations for future work will be discussed.
