123 results found
Șerban O, Thapen N, Maginnis B, et al., 2018, Real-time processing of social media with SENTINEL: A syndromic surveillance system incorporating deep learning for health classification, Information Processing and Management, ISSN: 0306-4573
© 2018 The Authors Interest in real-time syndromic surveillance based on social media data has greatly increased in recent years. The ability to detect disease outbreaks earlier than traditional methods would be highly useful for public health officials. This paper describes a software system which is built upon recent developments in machine learning and data processing to achieve this goal. The system is built from reusable modules integrated into data processing pipelines that are easily deployable and configurable. It applies deep learning to the problem of classifying health-related tweets and is able to do so with high accuracy. It has the capability to detect illness outbreaks from Twitter data and then to build up and display information about these outbreaks, including relevant news articles, to provide situational awareness. It also provides nowcasting functionality of current disease levels from previous clinical data combined with Twitter data. The preliminary results are promising, with the system being able to detect outbreaks of influenza-like illness symptoms which could then be confirmed by existing official sources. The Nowcasting module shows that using social media data can improve prediction for multiple diseases over simply using traditional data sources.
Kodagoda N, Pontis S, Simmie D, et al., 2017, Using Machine Learning to Infer Reasoning Provenance From User Interaction Log Data: Based on the Data/Frame Theory of Sensemaking, JOURNAL OF COGNITIVE ENGINEERING AND DECISION MAKING, Vol: 11, Pages: 23-41, ISSN: 1555-3434
Li T, Hankin C, 2017, Effective defence against zero-day exploits using bayesian networks, Pages: 123-136, ISSN: 0302-9743
© 2017, Springer International Publishing AG. Industrial Control Systems (ICS) play a crucial role in controlling industrial processes. Unlike conventional IT systems or networks, cyber attacks against ICS can cause destructive physical damage. Zero-day exploits (i.e. unknown exploits) have demonstrated their essential contributions to causing such damage by Stuxnet. In this work, we investigate the possibility of improving the tolerance of a system against zero-day attacks by defending against known weaknesses of the system. We first propose a metric to measure the system tolerance against zero-day attacks, which is the minimum effort required by zero-day exploits to compromise a system. We then apply this metric to evaluate different defensive plans to decide the most effective one in maximising the system tolerance against zero-day attacks. A case study about ICS security management is demonstrated in this paper.
Martin G, Kinross J, Hankin C, 2017, Effective cybersecurity is fundamental to patient safety, BMJ-BRITISH MEDICAL JOURNAL, Vol: 357, ISSN: 1756-1833
Fielder A, Li T, Hankin C, 2016, Modelling cost-effectiveness of defenses in industrial control systems, Pages: 187-200, ISSN: 0302-9743
© Springer International Publishing Switzerland 2016. Industrial Control Systems (ICS) play a critical role in controlling industrial processes. Wide use of modern IT technologies enables cyber attacks to disrupt the operation of ICS. Advanced Persistent Threats (APT) are the most threatening attacks to ICS due to their long persistence and destructive cyber-physical effects to ICS. This paper considers a simulation of attackers and defenders of an ICS, where the defender must consider the cost-effectiveness of implementing defensive measures within the system in order to create an optimal defense. The aim is to identify the appropriate deployment of a specific defensive strategy, such as defense-in-depth or critical component defense. The problem is represented as a strategic competitive optimisation problem, which is solved using a co-evolutionary particle swarm optimisation algorithm. Through the development of optimal defense strategy, it is possible to identify when each specific defensive strategies is most appropriate; where the optimal defensive strategy depends on the resources available and the relative effectiveness of those resources.
Fielder A, Li T, Hankin C, 2016, Defense-in-depth vs. Critical Component Defense for Industrial Control Systems., Publisher: BCS
Fielder A, Panaousis E, Malacaria P, et al., 2016, Decision support approaches for cyber security investment, DECISION SUPPORT SYSTEMS, Vol: 86, Pages: 13-23, ISSN: 0167-9236
Hankin C, 2016, Game Theory and Industrial Control Systems, Editors: Probst, Hankin, Hansen, Publisher: SPRINGER INT PUBLISHING AG, Pages: 178-190, ISBN: 978-3-319-27809-4
Khouzani MHR, Malacaria P, Hankin C, et al., 2016, Efficient Numerical Frameworks for Multi-objective Cyber Security Planning, 21st European Symposium on Research in Computer Security (ESORICS), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 179-197, ISSN: 0302-9743
Probst CW, Hankin C, Hansen RR, 2016, Semantics, logics, and calculi: Essays dedicated to Hanne Riis Nielson and Flemming Nielson on the occasion of their 60th birthdays, ISBN: 9783319278094
Thapen N, Simmie D, Hankin C, 2016, The early bird catches the term: combining twitter and news data for event detection and situational awareness, JOURNAL OF BIOMEDICAL SEMANTICS, Vol: 7, ISSN: 2041-1480
Thapen N, Simmie D, Hankin C, et al., 2016, DEFENDER: Detecting and Forecasting Epidemics Using Novel Data-Analytics for Enhanced Response, PLOS ONE, Vol: 11, ISSN: 1932-6203
Thapen NA, Simmie DS, Hankin C, 2016, The early bird catches the term: combining twitter and news data for event detection and situational awareness., J. Biomedical Semantics, Vol: 7, Pages: 61-61
Fielder A, Panaousis EA, Malacaria P, et al., 2015, Comparing Decision Support Approaches for Cyber Security Investment., CoRR, Vol: abs/1502.05532
Li T, Hankin C, 2015, A Model-based Approach to Interdependency between Safety and Security in ICS., Publisher: BCS
Vigliotti MG, Hankin C, 2015, Discovery of anomalous behaviour in temporal networks, SOCIAL NETWORKS, Vol: 41, Pages: 18-25, ISSN: 0378-8733
Fielder A, Panaousis E, Malacaria P, et al., 2014, Game Theory Meets Information Security Management, ICT SYSTEMS SECURITY AND PRIVACY PROTECTION, IFIP TC 11 INTERNATIONAL CONFERENCE, SEC 2014, Vol: 428, Pages: 15-29, ISSN: 1868-4238
Le Martelot E, Hankin C, 2014, Fast multi-scale detection of overlapping communities using local criteria, COMPUTING, Vol: 96, Pages: 1011-1027, ISSN: 0010-485X
Panaousis E, Fielder A, Malacaria P, et al., 2014, Cybersecurity Games and Investments: A Decision Support Approach, DECISION AND GAME THEORY FOR SECURITY, GAMESEC 2014, Vol: 8840, Pages: 266-286, ISSN: 0302-9743
Simmie D, Vigliotti MG, Hankin C, 2014, Ranking twitter influence by combining network centrality and influence observables in an evolutionary model, Journal of Complex Networks, Vol: 2, Pages: 495-517, ISSN: 2051-1310
© The authors 2014. Influential agents in networks play a pivotal role in information diffusion. Influence may rise or fall quickly over time and thus capturing this evolution of influence is of benefit to a varied number of application domains such as digital marketing, counter-terrorism or policing. In this paper, we investigate the influence of users in programming communities on Twitter. We propose a new model for capturing both time-invariant influence and also temporal influence. The unified model is a combination of network topological methods and observation of influence-relevant events in the network. We provide an application of Hidden Markov Models (HMM) for capturing this effect on the network. There are many possible combinations of influence factors, hence we required a ground-truth for model configuration. We performed a primary survey of our population users to elicit their views on influential users. The survey allowed us to validate the results of our classifier. We introduce a novel reward-based transformation to the Viterbi path of the observed sequences, which provides an overall ranking for users. Our results show an improvement in ranking accuracy over using solely topology-based methods for the particular area of interest we sampled. Utilizing the evolutionary aspect of the HMM, we attempt to predict future states using current evidence. Our prediction algorithm significantly outperforms a collection of naive models, especially in the short term (1-3 weeks).
Hankin C, 2013, A short note on Simulation and Abstraction, Electronic Proceedings in Theoretical Computer Science, EPTCS, Vol: 129, Pages: 337-340, ISSN: 2075-2180
This short note is written in celebration of David Schmidt's sixtieth birthday. He has now been active in the program analysis research community for over thirty years and we have enjoyed many interactions with him. His work on characterising simulations between Kripke structures using Galois connections was particularly influential in our own work on using probabilistic abstract interpretation to study Larsen and Skou's notion of probabilistic bisimulation. We briefly review this work and discuss some recent applications of these ideas in a variety of different application areas.
Hankin C, Malacaria P, 2013, Payoffs, intensionality and abstraction in games, Pages: 69-82, ISSN: 0302-9743
We discuss some fundamental concepts in Game Theory: the concept of payoffs and the relation between rational solutions to games like Nash equilibrium and real world behaviour. We sketch some connections between Game Theory and Game Semantics by exploring some possible uses of Game Semantics strategies enriched with payoffs. Finally we discuss potential contributions of Abstract Interpretation to Game Theory in addressing the state explosion problem of game models of real world systems. © 2013 Springer-Verlag Berlin Heidelberg.
Le Martelot E, Hankin C, 2013, Multi-scale community detection using stability optimisation, International Journal of Web Based Communities, Vol: 9, Pages: 323-348, ISSN: 1477-8394
Many real systems can be represented as networks whose analysis can be very informative regarding the original system's organisation. In the past decade, community detection received a lot of attention and is now a very active field of research. Recently, stability was introduced as a new measure for partition quality. This work investigates stability as an optimisation criterion that exploits a Markov process view of networks to enable multi-scale community detection. Several heuristics and variations of an algorithm optimising stability are presented as well as an application to overlapping communities. Experiments show that the method enables accurate multi-scale network analysis. Copyright © 2013 Inderscience Enterprises Ltd.
Le Martelot E, Hankin C, 2013, Fast Multi-Scale Detection of Relevant Communities in Large-Scale Networks, COMPUTER JOURNAL, Vol: 56, Pages: 1136-1150, ISSN: 0010-4620
Martelot EL, Hankin C, 2013, Fast Multi-Scale Community Detection based on Local Criteria within a Multi-Threaded Algorithm, CoRR, Vol: abs/1301.0955
Simmie D, Vigliotti MG, Hankin C, 2013, Ranking Twitter Influence by Combining Network Centrality and Influence Observables in an Evolutionary Model, 2013 INTERNATIONAL CONFERENCE ON SIGNAL-IMAGE TECHNOLOGY & INTERNET-BASED SYSTEMS (SITIS), Pages: 486-493
Yang F, Hankin C, Nielson F, et al., 2013, Predictive access control for distributed computation, SCIENCE OF COMPUTER PROGRAMMING, Vol: 78, Pages: 1264-1277, ISSN: 0167-6423
Martelot EL, Hankin C, 2012, Fast Multi-Scale Detection of Relevant Communities, CoRR, Vol: abs/1204.1002
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.