Research on keystroke dynamics biometrics has been increasing, especially in the last decade. The main motivation behind this effort is due to the fact that keystroke dynamics biometrics is economical and can be easily integrated into the existing computer security systems with minimal alteration and user intervention. Numerous studies have been conducted in terms of data acquisition devices, feature representations, classification methods, experimental protocols, and evaluations. However, an up-to-date extensive survey and evaluation is not yet available. The objective of this paper is to provide an insightful survey and comparison on keystroke dynamics biometrics research performed throughout the last three decades, as well as offering suggestions and possible future research directions.

There have been research activities in the area of keystroke dynamics biometrics on physical keyboards (desktop computers or conventional mobile phones) undertaken in the past three decades. However, in terms of touch dynamics biometrics on virtual keyboards (modern touchscreen mobile devices), there has been little published work. Particularly, there is a lack of an extensive survey and evaluation of the methodologies adopted in the area. Owing to the widespread use of touchscreen mobile devices, it is necessary for us to examine the techniques and their effectiveness in the domain of touch dynamics biometrics. The aim of this paper is to provide some insights and comparative analysis of the current state-of-the-art in the topic area, including data acquisition protocols, feature data representations, decision making techniques, as well as experimental settings and evaluations. With such a survey, we can gain a better understanding of the current state-of-the-art, thus identifying challenging issues and knowledge gaps for further research.

Mobile devices, particularly the touch screen mobile devices, are increasingly used to store and access private and sensitive data or services, and this has led to an increased demand for more secure and usable security services, one of which is user authentication. Currently, mobile device authentication services mainly use a knowledge-based method, e.g. a PIN-based authentication method, and, in some cases, a fingerprint-based authentication method is also supported. The knowledgebased method is vulnerable to impersonation attacks, while the fingerprint-based method can be unreliable sometimes. To overcome these limitations and to make the authentication service more secure and reliable for touch screen mobile device users, we have investigated the use of touch dynamics biometrics as a mobile device authentication solution by designing, implementing and evaluating a touch dynamics authentication method. This paper describes the design, implementation, and evaluation of this method, the acquisition of raw touch dynamics data, the use of the raw data to obtain touch dynamics features, and the training of the features to build an authentication model for user identity verification. The evaluation results show that by integrating the touch dynamics authentication method into the PIN-based authentication method, the protection levels against impersonation attacks is greatly enhanced. For example, if a PIN is compromised, the success rate of an impersonation attempt is drastically reduced from 100% (if only a 4-digit PIN is used) to 9.9% (if both the PIN and the touch dynamics are used).

No abstract

A behavior is considered abnormal when it is seen as unusual under certain contexts. The definition for abnormal behavior varies depending on situations. For example, people running in a field is considered normal but is deemed abnormal if it takes place in a mall. Similarly, loitering in the alleys, fighting or pushing each other in public areas are considered abnormal under specific circumstances. Abnormal behavior detection is crucial due to the increasing crime rate in the society. If an abnormal behavior can be detected earlier, tragedies can be avoided. In recent years, deep learning has been widely applied in the computer vision field and has acquired great success for human detection. In particular, Convolutional Neural Network (CNN) has shown to have achieved state-ofthe-art performance in human detection. In this paper, a CNN-based abnormal behavior detection method is presented. The proposed approach automatically learns the most discriminative characteristics pertaining to human behavior from a large pool of videos containing normal and abnormal behaviors. Since the interpretation for abnormal behavior varies across contexts, extensive experiments have been carried out to assess various conditions and scopes including crowd and single person behavior detection and recognition. The proposed method represents an end-to-end solution to deal with abnormal behavior under different conditions including variations in background, number of subjects (individual, two persons or crowd), and a range of diverse unusual human activities. Experiments on five benchmark datasets validate the performance of the proposed approach.