Liakat Ali

Keystroke Biometric Systems for User Authentication

Keystroke biometrics (KB) authentication systems are a less popular form of access control, although they are gaining popularity. In recent years, keystroke biometric authentication has been an active area of research due to its low cost and ease of integration with existing security systems. Various researchers have used different methods and algorithms for data collection, feature representation, classification, and performance evaluation to measure the accuracy of the system, and therefore achieved different accuracy rates. Although recently, the support vector machine is most widely used by researchers, it seems that ensemble methods and artificial neural networks yield higher accuracy. Moreover, the overall accuracy of KB is still lower than other biometric authentication systems, such as iris. The objective of this paper is to present a detailed survey of the most recent researches on keystroke dynamic authentication, the methods and algorithms used, the accuracy rate, and the shortcomings of those researches. Finally, the paper identifies some issues that need to be addressed in designing keystroke dynamic biometric systems, makes suggestions to improve the accuracy rate of KB systems, and proposes some possible future research directions.

Authentication and Identification Methods Used in Keystroke Biometric Systems

Keystroke dynamics authentication is not as widely used compared to other biometric systems. In recent years, keystroke dynamic authentication systems have gained interest because of low cost and integration with existing security systems. Many different methods have been proposed for data collection, feature representation, classification, and performance evaluation. The work presents a detailed survey of the most recent research in keystroke dynamic authentication. Research is evaluated by the conditions under which data was collected, classification algorithms used, and system performance. This work also identifies some shortcomings of the current research issues that need to be addressed for keystroke dynamics to mature. Some recommendations for future research are made, with the goal of improving keystroke dynamics system performance and robustness.

An Investigation on Cyber Security Threats and Security Models

Cyber security has been used interchangeably for information security, where later considers the role of the human in the security process while former consider this as an additional dimension and also, focus person has a potential target. However, such discussion on cyber security has important implication as it focuses on the ethical part of the society as a whole. To address the issue of cyber security, various frameworks and models have been developed. It also introduces the concepts of cyber security in terms of its framework, workforces and information related to protecting personal information in the computer. This paper reviews these models along with their limitations and review the past techniques used to mitigate these threats. Furthermore, the report also provides recommendations for future research.

An Analysis of Information Security Event Managers

The most effective security starts with real time visibility into all activity on all systems, networks, database and applications. In this paper the focus in on structured data however, some semi-structured and unstructured data is also explored. Whether the source is from network traffic, user activity, or the application user, any variation from normal of abnormal activity could indicate that a threat is imminent and that your data or infrastructure is at risk. In the last several years, there has been a disturbing trend in which attackers are innovating much faster than the defenders. There has been a commercialization of malware with attack kits available through underground forums for anyone who wants to perpetrate any variety of attacks. Large botnets are available for rent, allowing attackers to send spam or launch DDos (distributed denial-of-service) attacks. Many attackers reuse malware and command and control (C & C) and methods, adapting their products over time to keep ahead of the anti malware industry and security professionals. This paper surveys ESMs (Enterprise Security Managers) and cyber-attack case studies.

Spoofing key-press latencies with a generative keystroke dynamics model

This work provides strong empirical evidence for a two-state generative model of typing behavior in which the user can be in either a passive or active state. Given key-press latencies with missing key names, the model is then used to spoof the key-press latencies of a user by exploiting the scaling behavior between inter-key distance and key-press latency. Key-press latencies with missing key names can be remotely obtained over a network by observing traffic from an interactive application, such as SSH in interactive mode. The proposed generative model uses this partial information to perform a key-press-only sample-level attack on a victims keystroke dynamics template. Results show that some users are more susceptible to this type of attack than others. For about 10% of users, the spoofed samples obtain classifier output scores of at least 50% of those obtained by authentic samples. With at least 50 observed keystrokes, the chance of success over a zero-effort attack doubles on average.

Keystroke Biometric User Verification Using Hidden Markov Model

Biometric systems such as fingerprint, iris, DNA became popular methods in user authentication. Compared to these biometric systems, keystroke biometric authentication systems have not gained so much attention because of lower accuracy compared to other biometric systems. A number of researches have been conducted on keystroke biometric using different generative and discriminative classifiers. As Hidden Markov Models have proven a great success in voice recognition, this study investigates Hidden Markov Models in keystroke dynamic. This paper proposes a novel user verification technique using 1-substate Hidden Markov Model through keystroke dynamic. To verify the effectiveness of the proposed system, extensive experiments have been conducted and 80% accuracy was achieved by the proposed system.

Connectivity, Traffic Flow and Applied Statistics in Cyber Security

This paper discusses research-based findings of the issues addressed by connectivity, traffic flow, and applied statistics in cyber security, hence their impacts thereof. In a brief but detailed approach, the paper addresses the impacts of the incorporation of aforementioned disciplines in cybersecurity, thus allowing for further research on them to enforce security in the cyber-ecosystem. The paper is divided into three sections, with the first section describing the emerging issues that face advances in connectivity of devices and the implications of cyber security to curb attacks. The second section is devoted to traffic flow monitoring for detection of attacks, thus, the role it plays in enforcing cyber security. Finally, the third section will illustrate how applied statistics using formulated mathematical models can be applied for the purpose of cyber security. In summary, this paper seeks to address that cyber security is a critical component for networks and must be considered to facilitate better network performance.

An Approach to Minimize Crossings in Phylogenetic Trees

Visualization of phylogenetic trees became popular and has been widely used in biology, taxonomy, cloud computing, and bioinformatics. Different phylogenetic trees can be built based on different measures and methods. As a result, the problem became obvious when deciding which tree is better and most visually appealing. This often involves comparing two phylogenetic trees to each other. The main goal of this paper is to display a pair of alternative phylogenetic trees together while minimizing the number of crossings among the branches of both trees. This paper summarizes different tools and techniques used in visualizing phylogenetic trees in different studies and describes their limitations. After surveying different studies involved in crossings minimization, a naive algorithm to minimize the number of crossings is proposed.

Developing Virtual Residential Area using Virtual Reality Modeling Language and Virtual Reality Tools

Virtual reality is one of the most developing parts of computer science and engineering. It has opened the door of new possibilities in the field of computer science and engineering. It is also currently being examined for practical use in various industrial fields. One contribution of this paper is that it provides a real example of virtual reality in industrial applications which may encourage the scientists to develop virtual reality model. The paper also discusses shortly about the current use of virtual reality tools, their uses in various sectors of science and engineering and proposes theoretically an application of virtual reality system for developing residential area. One programming language, virtual reality modeling language is presented in development of computer visualization tools for the system. By using high resolution display, three dimension computer graphics, and interactive device, a virtual world can be realized in which imaginary objects created by VRML can be picked up as if they are in real world.