A Context-Aware Recommendation System to Behavioral Based Authentication in Mobile and Pervasive Environments

Abstract

Mobile devices use traditional authentication processes, which are vulnerable and unsuitable for highly dynamic environments, such as ubiquitous and pervasive environments. Therefore, new approaches are necessary in such environments. These approaches must be (i) context-aware by considering environmental and operational characteristics, restrictions of devices and information provided by sensors within the pervasive space; and (ii) customizable for balancing the systems proactivity with the control that the user wants to have over his systems. In this paper, it is presented an approach that provides a recommendation system based on the user behavior and the pervasive space where he belongs. The user behavior is defined by the actions and events that compose the activity that is being performed. The experimental results indicate (a) a dynamic and autonomic mechanism, which is more suitable for authenticating users in mobile and pervasive environments, and (b) significant efficiency to detect authentication anomalies by using a similarity model and a spatio-temporal permutation model.

Extended sammon projection and wavelet kernel extreme learning machine for gait-based legitimate user identification

“…Moreover, the idea behind the behavior-based model is that the person's habits are a set of its attributes; therefore, each event (activity) has a correlation between two fundamental attributes: space and time. In addition, the architecture proposed in [39], utilizes the resources found in the smartphone devices, such as user calls, user schedule, GPS, device battery level, user applications, and sensors. A similar methodology has also been adopted in [45].…”

Modern Authentication Techniques in Smart Phones: Security and Usability Perspective

“…These are vulnerable for highly dynamic environments, therefore in such environments need of new approaches to be implemented. These new approaches must be context aware of environment and customizable that a user wants to have over his systems [62]. Here user can be authenticated by using data captured by sensors at of the mobile device and the behavior of the user.…”

A novel identification/verification model using smartphone's sensors and user behavior

“…A user behavioral model is provided in [1], the corresponding research is based on the idea that the person is a creature of habit, therefore each event has a correlation between two fundamental attributes: space and time. The proposed architecture uses resources found in the mobile devices: User calls, user schedule, GPS, device battery level, user applications, and sensors.…”

“…Generally, authentication and identification processes are increasing with the increase of services, causing the user, in general, to use short, easy, and repetitive passwords. These facts in addition to the possibility of stealing or losing the mobile, leads to security threats on the personal data [1]. More particularly, elderly and physically impaired users find difficulties by entering pin codes or screen patterns, or might be unable to do explicit authentication.…”