Greg Stephens

Artificial immune systems for the detection of credit card fraud: an architecture, prototype and preliminary results

Some biological phenomena offer clues to solving real‐life, complex problems. Researchers have been studying techniques such as neural networks and genetic algorithms for computational intelligence and their applications to such complex problems. The problem of security management is one of the major concerns in the development of eBusiness services and networks. Recent incidents have shown that the perpetrators of cybercrimes are using increasingly sophisticated methods. Hence, it is necessary to investigate non‐traditional mechanisms, such as biological techniques, to manage the security of evolving eBusiness networks and services. Towards this end, this paper investigates the use of an Artificial Immune System (AIS). The AIS emulates the mechanism of human immune systems that save human bodies from complex natural biological attacks. The paper discusses the use of AIS on one aspect of security management, viz. the detection of credit card fraud. The solution is illustrated with a case study on the management of frauds in credit card transactions, although this technique may be used in a range of security management applications in eBusiness.

Towards a Methodology for Profiling Cyber Criminals

The progress of future e-business and e-commerce will depend on the ability of our legal institutions to protect general users from cyber crimes. While there has been substantial progress in the development and implementation of tools for detecting and preventing cyber attacks, there is a lack of effective methodologies to prosecute the perpetrators of cyber crimes (cyber criminals). Consequently, many cyber crimes go unpunished and many intrusion detections tools go unutilized. Hence there is a need for holistic methodologies that can help organizations collect legally valid evidences from cyber crimes so that appropriate actions can be taken against cyber criminals. This paper presents an approach for this objective by using honeynets.

Knowledge discovery through visualising using virtual reality

Knowledge discovery and visualisation are important techniques for discovering and understanding patterns in large data sets. The study presents the development of a three dimensional virtual reality model that assists the user to visually explore structures and relationships in the collected data. The three dimensional model uses a combination of nodes and paths to represent objects/actors and the strength/direction of the measured characteristic. Virtual reality provides the mechanism for manipulation of the developed model in real time. Specifically, we demonstrate the potential of this visual tool by having postgraduate students, organised into focus groups, engage in a knowledge discovery exercise with data collected in an academic work environment. The method adopted to convert the identified relationships into a virtual reality model is discussed, as well as some of the additional features that could be incorporated using such a method.

Investigating the Applicability of Structural Analysis Techniques in Distributed Systems

An object-oriented system is comprised of a number of objects that work together to achieve a common goal. In a distributed system, these objects are distributed around a computer network to improve the overall performance or reliability of the system. However, care must be taken in the placement of the components because inappropriate assignment onto processors or subsystems can substantially degrade the performance of the system. The distribution process can be broken up into two stages, partitioning and allocation. Partitioning is the process of dividing the system into tasks; these tasks are then assigned to the system’s various processors in the allocation stage. This chapter describes a new approach to the distribution process and investigates the use of structural analysis as developed for social network analysis for making distribution process decisions.