skip to main content

Title: What is More Important for Touch Dynamics based Mobile User Authentication?
Mobile user authentication (MUA) has become a gatekeeper for securing a wealth of personal and sensitive information residing on mobile devices. Keystrokes and touch gestures are two types of touch behaviors. It is not uncommon for a mobile user to make multiple MUA attempts. Nevertheless, there is a lack of an empirical comparison of different types of touch dynamics based MUA methods across different attempts. In view of the richness of touch dynamics, a large number of features have been extracted from it to build MUA models. However, there is little understanding of what features are important for the performance of such MUA models. Further, the training sample size of template generation is critical for real-world application of MUA models, but there is a lack of such information about touch gesture based methods. This study is aimed to address the above research limitations by conducting experiments using two MUA prototypes. Their empirical results can not only serve as a guide for the design of touch dynamics based MUA methods but also offer suggestions for improving the performance of MUA models.
Authors:
Award ID(s):
1917537
Publication Date:
NSF-PAR ID:
10167262
Journal Name:
PACIS 2020 Proceedings
Sponsoring Org:
National Science Foundation
More Like this
  1. Despite that tremendous progress has been made in mobile user authentication (MUA) in recent years, continuous mobile user authentication (CMUA), in which authentication is performed continuously after initial login, remains under studied. In addition, although one-handed interaction with a mobile device becomes increasingly common, one-handed CMUA has never been investigated in the literature. There is a lack of investigation of the CMUA performance between one-handed and two-handed interactions. To fill the literature gap, we developed a new CMUA method based on touch dynamics of thumb scrolling on the touchscreen of a mobile device. We developed a mobile app of the proposed CMUA method and evaluated its effectiveness with data collected from a user study. The findings have implications for the design of effective CMUA using touch dynamics and for improvement of accessibility and usability of MUA mechanisms.
  2. Abstract

    The optimization of surface finish to improve performance, such as adhesion, friction, wear, fatigue life, or interfacial transport, occurs largely through trial and error, despite significant advancements in the relevant science. There are three central challenges that account for this disconnect: (1) the challenge of integration of many different types of measurement for the same surface to capture the multi-scale nature of roughness; (2) the technical complexity of implementing spectral analysis methods, and of applying mechanical or numerical models to describe surface performance; (3) a lack of consistency between researchers and industries in how surfaces are measured, quantified, and communicated. Here we present a freely-available internet-based application (available athttps://contact.engineering) which attempts to overcome all three challenges. First, the application enables the user to upload many different topography measurements taken from a single surface, including using different techniques, and then integrates all of them together to create a digital surface twin. Second, the application calculates many of the commonly used topography metrics, such as root-mean-square parameters, power spectral density (PSD), and autocorrelation function (ACF), as well as implementing analytical and numerical calculations, such as boundary element modeling (BEM) for elastic and plastic deformation. Third, the application servesmore »as a repository for users to securely store surfaces, and if they choose, to share these with collaborators or even publish them (with a digital object identifier) for all to access. The primary goal of this application is to enable researchers and manufacturers to quickly and easily apply cutting-edge tools for the characterization and properties-modeling of real-world surfaces. An additional goal is to advance the use of open-science principles in surface engineering by providing a FAIR database where researchers can choose to publish surface measurements for all to use.

    « less
  3. Hand-gesture and in-air-handwriting provide ways for users to input information in Augmented Reality (AR) and Virtual Reality (VR) applications where a physical keyboard or a touch screen is unavailable. However, understanding the movement of hands and fingers is challenging, which requires a large amount of data and data-driven models. In this paper, we propose an open research infrastructure named FMKit for in-air-handwriting analysis, which contains a set of Python libraries and a data repository collected from over 180 users with two different types of motion capture sensors. We also present three research tasks enabled by FMKit, including in-air-handwriting based user authentication, user identification, and word recognition, and preliminary baseline performance.
  4. Hand-gesture and in-air-handwriting provide ways for users to input information in Augmented Reality (AR) and Virtual Reality (VR) applications where a physical keyboard or a touch screen is unavailable. However, understanding the movement of hands and fingers is challenging, which requires a large amount of data and data-driven models. In this paper, we propose an open research infrastructure named FMKit for in-air-handwriting analysis, which contains a set of Python libraries and a data repository collected from over 180 users with two different types of motion capture sensors. We also present three research tasks enabled by FMKit, including in-air-handwriting based user authentication, user identification, and word recognition, and preliminary baseline performance.
  5. User and item reviews are valuable for the construction of recommender systems. In general, existing review-based methods for recommendation can be broadly categorized into two groups: the siamese models that build static user and item representations from their reviews respectively, and the interaction-based models that encode user and item dynamically according to the similarity or relationships of their reviews. Although the interaction-based models have more model capacity and fit human purchasing behavior better, several problematic model designs and assumptions of the existing interaction-based models lead to its suboptimal performance compared to existing siamese models. In this paper, we identify three problems of the existing interaction-based recommendation models and propose a couple of solutions as well as a new interaction-based model to incorporate review data for rating prediction. Our model implements a relevance matching model with regularized training losses to discover user relevant information from long item reviews, and it also adapts a zero attention strategy to dynamically balance the item-dependent and item-independent information extracted from user reviews. Empirical experiments and case studies on Amazon Product Benchmark datasets show that our model can extract effective and interpretable user/item representations from their reviews and outperforms multiple types of state-of-the-art review-based recommendation models.