
The contents of this volume are contributions from invited speakers at a workshop entitled “Data Analysis for Cyber-Security”, hosted by the Universityof Bristol in March2013.We aregrateful for the generous support of the Heilbronn Institute for Mathematical Research, an academic research unit of the Universisty of Bristol with interests related to cyber-security. Cyber-security – the task of defending computers and people from electronic attack – is a pressing concern. For example, a report sponsored by the UK government in 2012 estimated the cost of cyber-attack to the UK economy as £29 billion. This cost is attributed to various types of attack, including extortion, fiscal fraud and identity theft. Notably, the largest category,intellectualpropertytheft, accountedfor around£9billion. Thescale of cyber-attack provoked the UK government to highlight cyber-security as a top priority for national security in 2013. From a UK point of view, based on recent figures, the problem is increasing: 78% of large organisations were subject to external attack in 2012, up from 73% in the previous year, while 63% of small business were subject to such attack over the same period, an increase of 41% on the previous year. Cyber-security is a broad discipline, covering a range of academic disciplines including computer science, computer and network architecture, and statistics. This volume is concerned with network cyber-security, and particularly, analysis of data that are observed in relation to a network of either computers or people. As an exemplar, consider an institutional computer network, in which communicating devices (computers, printers, etc.) are nodes and communications between devices are events that occur on edges between nodes. Numerous types of cyber-attack have been observed in this context. A variety of such attacks are well described in Davidoff and Ham (2012) from the point of view of network forensics.
Data Analysis For Network Cyber-Security