Xavier Bellekens

The use of supervised Machine Learning (ML) to enhance Intrusion Detection Systems has been the subject of significant research. Supervised ML is based upon learning by example, demanding significant volumes of representative instances for effective training and the need to re-train the model for every unseen cyber-attack class. However, retraining the models in-situ renders the network susceptible to attacks owing to the time-window required to acquire a sufficient volume of data. Although anomaly detection systems provide a coarse-grained defence against unseen attacks, these approaches are significantly less accurate and suffer from high false-positive rates. Here, a complementary approach referred to as 'One-Shot Learning', whereby a limited number of examples of a new attack-class is used to identify a new attack-class (out of many) is detailed. The model grants a new cyber-attack classification without retraining. A Siamese Network is trained to differentiate between classes based on pairs similarities, rather than features, allowing to identify new and previously unseen attacks. The performance of a pre-trained model to classify attack-classes based only on one example is evaluated using three datasets. Results confirm the adaptability of the model in classifying unseen attacks and the trade-off between performance and the need for distinctive class representation.

The use of supervised Machine Learning (ML) to enhance Intrusion Detection Systems (IDS) has been the subject of significant research. Supervised ML is based upon learning by example, demanding significant volumes of representative instances for effective training and the need to retrain the model for every unseen cyber-attack class. However, retraining the models in-situ renders the network susceptible to attacks owing to the time-window required to acquire a sufficient volume of data. Although anomaly detection systems provide a coarse-grained defence against unseen attacks, these approaches are significantly less accurate and suffer from high false-positive rates. Here, a complementary approach referred to as “One-Shot Learning”, whereby a limited number of examples of a new attack-class is used to identify a new attack-class (out of many) is detailed. The model grants a new cyber-attack classification opportunity for classes that were not seen during training without retraining. A Siamese Network is trained to differentiate between classes based on pairs similarities, rather than features, allowing to identify new and previously unseen attacks. The performance of a pre-trained model to classify new attack-classes based only on one example is evaluated using three mainstream IDS datasets; CICIDS2017, NSL-KDD, and KDD Cup’99. The results confirm the adaptability of the model in classifying unseen attacks and the trade-off between performance and the need for distinctive class representations.

The integration of Information and Communication Technology (ICT) tools into mechanical devices in routine use within the aviation industry has heightened cyber-security concerns. The extent of the inherent vulnerabilities in the software tools that drive these systems escalates as the level of integration increases. Moreover, these concerns are becoming even more acute as the migration within the industry in the deployment of electronic-enabled aircraft and smart airports gathers pace. A review of cyber-security attacks and attack surfaces within the aviation sector over the last 20 years provides a mapping of the trends and insights that are of value in informing on future frameworks to protect the evolution of a key industry. The goal is to identify common threat actors, their motivations, attacks types and map the vulnerabilities within aviation infrastructures most commonly subject to persistent attack campaigns. The analyses will enable an improved understanding of both the current and potential future cyber-security protection provisions for the sector. Evidence is provided that the main threats to the industry arise from Advance Persistent Threat (APT) groups that operate, in collaboration with a particular state actor, to steal intellectual property and intelligence in order to advance their domestic aerospace capabilities as well as monitor, infiltrate and subvert other sovereign nations’ capabilities. A segment of the aviation industry commonly attacked is the Information Technology (IT) infrastructure, the most prominent type of attack being malicious hacking with intent to gain unauthorised access. The analysis of the range of attack surfaces and the existing threat dynamics has been used as a foundation to predict future cyber-attack trends. The insights arising from the review will support the future definition and implementation of proactive measures that protect critical infrastructures against cyber-incidents that damage the confidence of customers in a key service-oriented industry.

The paper presents a classification of cyber attacks within the context of the state of the art in the maritime industry. A systematic categorization of vessel components has been conducted, complemented by an analysis of key services delivered within ports. The vulnerabilities of the Global Navigation Satellite System (GNSS) have been given particular consideration since it is a critical subcategory of many maritime infrastructures and, consequently, a target for cyber attacks. Recent research confirms that the dramatic proliferation of cyber crimes is fueled by increased levels of integration of new enabling technologies, such as IoT and Big Data. The trend to greater systems integration is, however, compelling, yielding significant business value by facilitating the operation of autonomous vessels, greater exploitation of smart ports, a reduction in the level of manpower and a marked improvement in fuel consumption and efficiency of services. Finally, practical challenges and future research trends have been highlighted.

Machine Learning (ML) for developing Intrusion Detection Systems (IDS) is a fast-evolving research area that has many unsolved domain challenges. Current IDS models face two challenges that limit their performance and robustness. Firstly, they require large datasets to train and their performance is highly dependent on the dataset size. Secondly, zero-day attacks demand that machine learning models are retrained in order to identify future attacks of this type. However, the sophistication and increasing rate of cyber attacks make retraining time prohibitive for practical implementation. This paper proposes a new IDS model that can learn from pair similarities rather than class discriminative features. Learning similarities requires less data for training and provides the ability to flexibly adapt to new cyber attacks, thus reducing the burden of retraining. The underlying model is based on Siamese Networks, therefore, given a number of instances, numerous similar and dissimilar pairs can be generated. The model is evaluated using three mainstream IDS datasets; CICIDS2017, KDD Cup'99, and NSL-KDD. The evaluation results confirm the ability of the Siamese Network model to suit IDS purposes by classifying cyber attacks based on similarity-based learning. This opens a new research direction for building adaptable IDS models using non-conventional ML techniques.

With the rapid growth of the contemporary Internet of Things (IoT) market, the established systems raise a number of concerns regarding the reliability and the potential presence of critical integration defects. In this paper, we present a PatrIoT framework that aims to provide flexible support to construct an effective IoT system testbed to implement automated interoperability and integration testing. The framework allows scaling from a pure physical testbed to a simulated environment using a number of predefined modules and elements to simulate an IoT device or part of the tested infrastructure. PatrIoT also contains a set of reference example testbeds and several sets of example automated tests for a smart street use case.

Cyber-attacks continue to grow, both in terms of volume and sophistication. This is aided by an increase in available computational power, expanding attack surfaces, and advancements in the human understanding of how to make attacks undetectable. Unsurprisingly, machine learning is utilised to defend against these attacks. In many applications, the choice of features is more important than the choice of model. A range of studies have, with varying degrees of success, attempted to discriminate between benign traffic and well-known cyber-attacks. The features used in these studies are broadly similar and have demonstrated their effectiveness in situations where cyber-attacks do not imitate benign behaviour. To overcome this barrier, in this manuscript, we introduce new features based on a higher level of abstraction of network traffic. Specifically, we perform flow aggregation by grouping flows with similarities. This additional level of feature abstraction benefits from cumulative information, thus qualifying the models to classify cyber-attacks that mimic benign traffic. The performance of the new features is evaluated using the benchmark CICIDS2017 dataset, and the results demonstrate their validity and effectiveness. This novel proposal will improve the detection accuracy of cyber-attacks and also build towards a new direction of feature extraction for complex ones.