Organisations and governments constantly face potential security attacks. However, the need for next-generation cyber defence has become even more urgent in a day age when attack surfaces that hackers can exploit have grown at an alarming rate with increase number of devices are connected to Internet. As such, relies on predictive analysis is proactive than existing technologies rely intrusion ...

Abstract In recent years, Graph Neural Networks (GNNs) have achieved excellent applications in classification or prediction tasks. Recent studies demonstrated that GNNs are vulnerable to adversarial attacks. Modification Attack (GMA) and Injection (GIA) commonly attack strategies. Most graph methods based on GMA, which has a clear drawback: the attacker needs high privileges modify original gra...

This paper presents an evolutionary algorithm that learns attack scenarios, called attack specifications, from a network graph. This learning process aims to find attack specifications that minimise cost and maximise the value that an attacker gets from a successful attack. The attack specifications that the algorithm learns are represented using an approach based on Hoare’s CSP (Communicating ...

Databases are an integral part of almost any computing system today, and users heavily rely on the services they provide. When we interact with a computing system, we expect that any data be stored for future use, that the data is able to be looked up quickly, and that we can perform complex queries against the data stored in the database. There are many different emerging database types availa...

Consider a patrol problem, where a patroller traverses a graph through edges to detect potential attacks at nodes. An attack takes a random amount of time to complete. The patroller takes one time unit to move to and inspect an adjacent node, and will detect an ongoing attack with some probability. If an attack completes before it is detected, a cost is incurred. The attack time distribution, t...

Real world planners need to be sensitive to the quality of the plans they generate. Unlike classical planning where quality is often synonymous with plans having least number of actions, in temporal planning plan quality is multidimensional. It involves both temporal aspects of the plan (such as makespan, slack, tardiness) and execution cost aspects (such as cumulative action cost, resource con...

Software-Defined Networking-based Mobile Networks (SDN-MNs) are considered the future of 5G mobile network architecture. With the evolving cyber-attack threat, security assessments need to be performed in the network management. Due to the distinctive features of SDN-MNs, such as their dynamic nature and complexity, traditional network security assessment methodologies cannot be applied directl...

Guess-and-determine attack is one of the general attacks on stream ciphers. It is a common cryptanalysis tool for evaluating security of stream ciphers. The effectiveness of this attack is based on the number of unknown bits which will be guessed by the attacker to break the cryptosystem. In this work, we present a relation between the minimum numbers of the guessed bits and uniquely restricted...

Today’s computer systems face sophisticated attackers who combine multiple vulnerabilities to penetrate networks with devastating impact. The overall security of a network cannot be determined by simply counting the number of vulnerabilities. To accurately assess the security of networked systems, one must understand how vulnerabilities can be combined to stage an attack. We model such composit...