Biblio

This research concerns the detection of unauthorised access within hospital networks through the real-time analysis of audit logs. Privacy is a primary concern amongst patients due to the rising adoption of Electronic Patient Record (EPR) systems. There is growing evidence to suggest that patients may withhold information from healthcare providers due to lack of Trust in the security of EPRs. Yet, patient record data must be available to healthcare providers at the point of care. Ensuring privacy and confidentiality of that data is challenging. Roles within healthcare organisations are dynamic and relying on access control is not sufficient. Through proactive monitoring of audit logs, unauthorised accesses can be detected and presented to an analyst for review. Advanced data analytics and visualisation techniques can be used to aid the analysis of big data within EPR audit logs to identify and highlight pertinent data points. Employing a human-in-the-loop model ensures that suspicious activity is appropriately investigated and the data analytics is continuously improving. This paper presents a system that employs a Human-in-the-Loop Machine Learning (HILML) algorithm, in addition to a density-based local outlier detection model. The system is able to detect 145 anomalous behaviours in an unlabelled dataset of 1,007,727 audit logs. This equates to 0.014% of the EPR accesses being labelled as anomalous in a specialist Liverpool (UK) hospital.

The proliferation of malware attacks causes a hindrance to cybersecurity thus, posing a significant threat to our devices. The variety and number of both known as well as unknown malware makes it difficult to detect it. Research suggests that the ramifications of malware are only becoming worse with time and hence malware analysis becomes crucial. This paper proposes a visual malware classification technique to convert malware executables into their visual representations and obtain grayscale images of malicious files. These grayscale images are then used to classify malicious files into their respective malware families by passing them through deep convolutional neural networks (CNN). As part of deep CNN, we use various ImageNet models and compare their performance.

Experimentation focused on assessing the value of complex visualisation approaches when compared with alternative methods for data analysis is challenging. The interaction between participant prior knowledge and experience, a diverse range of experimental or real-world data sets and a dynamic interaction with the display system presents challenges when seeking timely, affordable and statistically relevant experimentation results. This paper outlines a hybrid approach proposed for experimentation with complex interactive data analysis tools, specifically for computer network traffic analysis. The approach involves a structured survey completed after free engagement with the software platform by expert participants. The survey captures objective and subjective data points relating to the experience with the goal of making an assessment of software performance which is supported by statistically significant experimental results. This work is particularly applicable to field of network analysis for cyber security and also military cyber operations and intelligence data analysis.

Phishing attacks continue to be one of the most common attack vectors used online today to deceive users, such that attackers can obtain unauthorised access or steal sensitive information. Phishing campaigns often vary in their level of sophistication, from mass distribution of generic content, such as delivery notifications, online purchase orders, and claims of winning the lottery, through to bespoke and highly-personalised messages that convincingly impersonate genuine communications (e.g., spearphishing attacks). There is a distinct trade-off here between the scale of an attack versus the effort required to curate content that is likely to convince an individual to carry out an action (typically, clicking a malicious hyperlink). In this short paper, we conduct a preliminary study on a recent realworld incident that strikes a balance between attacking at scale and personalised content. We adopt different visualisation tools and techniques for better assessing the scale and impact of the attack, that can be used both by security professionals to analyse the security incident, but could also be used to inform employees as a form of security awareness and training. We pitched the approach to IT professionals working in information security, who believe this may provide improved awareness of how targeted phishing campaigns can impact an organisation, and could contribute towards a pro-active step of how analysts will examine and mitigate the impact of future attacks across the organisation.

Cyberspace is ubiquitous and is becoming increasingly critical to many societal, commercial, military, and national functions as it emerges as an operational space in its own right. Within this context, decision makers must achieve mission continuity when operating in cyberspace. One aspect of any comprehensive security program is the use of penetration testing; the use of scanning, enumeration and offensive techniques not unlike those used by a potential adversary. Effective penetration testing provides security insight into the network as a system in its entirety. Often though, this systemic view is lost in reporting outcomes, instead becoming a list of vulnerable or exploitable systems that are individually evaluated for remediation priority. This paper introduces Trogdor; a mission-centric automated cyber red-teaming system. Trogdor undertakes model based Automated Cyber Red Teaming (ACRT) and critical node analysis to visually present the impact of vulnerable resources to cyber dependent missions. Specifically, this work discusses the purpose of Trogdor, outlines its architecture, design choices and the technologies it employs. This paper describes an application of Trogdor to an enterprise network scenario; specifically, how Trogdor provides an understanding of potential mission impacts arising from cyber vulnerabilities and mission or business-centric decision support in selecting possible strategies to mitigate those impacts.

As digital objects become increasingly important in people's lives, people may need to understand the provenance, or lineage and history, of an important digital object, to understand how it was produced. This is particularly important for objects created from large, multi-source collections of personal data. As the metadata describing provenance, Provenance Data, is commonly represented as a labelled directed acyclic graph, the challenge is to create effective interfaces onto such graphs so that people can understand the provenance of key digital objects. This unsolved problem is especially challenging for the case of novice and intermittent users and complex provenance graphs. We tackle this by creating an interface based on a clustering approach. This was designed to enable users to view provenance graphs, and to simplify complex graphs by combining several nodes. Our core contribution is the design of a prototype interface that supports clustering and its analytic evaluation in terms of desirable properties of visualisation interfaces.