Blockchain technology offers a decentralized and secure platform for addressing various challenges in smart cities and cyber-physical systems, including identity management, trust and transparency, and supply chain management. However, blockchains are susceptible to a variety of threats, akin to any other technological system. To assess the resilience and robustness of diverse blockchain technologies, this study evaluates their performance indicators under various attack scenarios. Therefore, this study conducts a thorough examination of multiple well-known blockchain technologies, such as Ethereum and Hyperledger Fabric, under Distributed Denial of Service attack scenarios. Ethereum, introduced as a revolutionary blockchain technology, has entirely transformed the way smart contracts and decentralized applications operate. Additionally, the innovative open source blockchain framework, Hyperledger Fabric, is intended for businesses and alliances seeking a secure and adaptable platform to develop distributed ledger applications. Hyperledger Besu, an Ethereum client with an extractable Ethereum Virtual Machine implementation designed to be enterprise-friendly for both public and private permissioned network use cases. Therefore, Ethereum and Hyperledger Fabric are utilized in this study for performance comparison. This study provides a summary of Ethereum's salient characteristics, architecture, and noteworthy influence on the blockchain and cryptocurrency ecosystem. Furthermore, it offers an overview of the main characteristics, architecture, and potential uses of Hyperledger Fabric. The blockchain's resilience against DDoS attacks is assessed by examining performance measures such as latency and throughput, which are fundamental metrics crucial for evaluating and enhancing the effectiveness of various systems, including communication protocols, databases, blockchains, and computer networks. The outcomes of these experiments show that Hyperledger Fabric has greater throughput and reduced latency, demonstrating its resistance to DDoS attacks in comparison with Ethereum. Ethereum, being a permissionless blockchain, can introduce challenges such as the potential for network congestion and scalability issues.

Ensuring strict adherence to security during the phases of Android app development is essential, primarily due to the prevalent issue of apps being released without adequate security measures in place. While a few automated tools are employed to reduce potential vulnerabilities during development, their effectiveness in detecting vulnerabilities may fall short. To address this, “Defendroid”, a blockchain-based federated neural network enhanced with Explainable Artificial Intelligence (XAI) is introduced in this work. Trained on the LVDAndro dataset, the vanilla neural network model achieves a 96% accuracy and 0.96 F1-Score in binary classification for vulnerability detection. Additionally, in multi-class classification, the model accurately identifies Common Weakness Enumeration (CWE) categories with a 93% accuracy and 0.91 F1-Score. In a move to foster collaboration and model improvement, the model has been deployed within a blockchain-based federated environment. This environment enables community-driven collaborative training and enhancements in partnership with other clients. The extended model demonstrates improved accuracy of 96% and F1-Score of 0.96 in both binary and multi-class classifications. The use of XAI plays a pivotal role in presenting vulnerability detection results to developers, offering prediction probabilities for each word within the code. This model has been integrated into an Application Programming Interface (API) as the backend and further incorporated into Android Studio as a plugin, facilitating real-time vulnerability detection. Notably, Defendroid exhibits high efficiency, delivering prediction probabilities for a single code line in an average processing time of a mere 300 ms. The weight-sharing transparency in the blockchain-driven federated model enhances trust and traceability, fostering community engagement while preserving source code privacy and contributing to accuracy improvement.

Modelling and controlling heat transfer in rotating electrical machines is very important as it enables the design of assemblies (e.g., motors) that are efficient and durable under multiple operational scenarios. To address the challenge of deriving accurate data-driven estimators of key motor temperatures, we propose a multi-objective strategy for creating Linear Regression (LR) models that integrate optimised synthetic features. The main strength of our approach is that it provides decision makers with a clear overview of the optimal tradeoffs between data collection costs, the expected modelling errors and the overall explainability of the generated thermal models. Moreover, as parsimonious models are required for both microcontroller deployment and domain expert interpretation, our modelling strategy contains a simple but effective step-wise regularisation technique that can be applied to outline domain-relevant mappings between LR variables and thermal profiling capabilities. Results indicate that our approach can generate accurate LR-based dynamic thermal models when training on data associated with a limited set of load points within the safe operating area of the electrical machine under study.

Ensuring the security of Android applications is a vital and intricate aspect requiring careful consideration during development. Unfortunately, many apps are published without sufficient security measures, possibly due to a lack of early vulnerability identification. One possible solution is to employ machine learning models trained on a labelled dataset, but currently, available datasets are suboptimal. This study creates a sequence of datasets of Android source code vulnerabilities, named LVDAndro, labelled based on Common Weakness Enumeration (CWE). Three datasets were generated through app scanning by altering the number of apps and their sources. The LVDAndro, includes over 2,000,000 unique code samples, obtained by scanning over 15,000 apps. The AutoML technique was then applied to each dataset, as a proof of concept to evaluate the applicability of LVDAndro, in detecting vulnerable source code using machine learning. The AutoML model, trained on the dataset, achieved accuracy of 94% and F1-Score of 0.94 in binary classification, and accuracy of 94% and F1-Score of 0.93 in CWE-based multi-class classification. The LVDAndro dataset is publicly available, and continues to expand as more apps are scanned and added to the dataset regularly. The LVDAndro GitHub Repository also includes the source code for dataset generation, and model training.

Modern automobiles are equipped with a large number of electronic control units (ECUs) to provide safe, driver assistance and comfortable services. The controller area network (CAN) provides near real-time data transmission between ECUs with adequate reliability for in-vehicle communication. However, the lack of security measures such as authentication and encryption makes the CAN bus vulnerable to cyberattacks, which affect the safety of passengers and the surrounding environment. Detecting attacks on the CAN bus, particularly masquerade attacks, presents significant challenges. It necessitates an intrusion detection system (IDS) that effectively utilizes both CAN ID and payload data to ensure thorough detection and protection against a wide range of attacks, all while operating within the constraints of limited computing resources. This paper introduces an ensemble IDS that combines a gated recurrent unit (GRU) network and a novel autoencoder (AE) model to identify cyberattacks on the CAN bus. AEs are expected to produce higher reconstruction errors for anomalous inputs, making them suitable for anomaly detection. However, vanilla AE models often suffer from overgeneralization, reconstructing anomalies without significant errors, resulting in many false negatives. To address this issue, this paper proposes a novel AE called Latent AE, which incorporates a shallow AE into the latent space. The Latent AE model utilizes Cramér’s statistic-based feature selection technique and a transformed CAN payload data structure to enhance its efficiency. The proposed ensemble IDS enhances attack detection capabilities by leveraging the best capabilities of independent GRU and Latent AE models, while mitigating the weaknesses associated with each individual model. The evaluation of the IDS on two public datasets, encompassing 13 different attacks, including sophisticated masquerade attacks, demonstrates its superiority over baseline models with near real-time detection latency of 25ms.

As a fundamental task in remote sensing observation of the earth, change detection using hyperspectral images (HSI) features high accuracy due to the combination of the rich spectral and spatial information, especially for identifying land-cover variations in bi-temporal HSIs. Relying on the image difference, existing HSI change detection methods fail to preserve the spectral characteristics and suffer from high data dimensionality, making them extremely challenging to deal with changing areas of various sizes. To tackle these challenges, we propose a cross-band 2-D self-attention Network (CBANet) for end-to-end HSI change detection. By embedding a cross-band feature extraction module into a 2-D spatial-spectral self-attention module, CBANet is highly capable of extracting the spectral difference of matching pixels by considering the correlation between adjacent pixels. The CBANet has shown three key advantages: 1) less parameters and high efficiency; 2) high efficacy of extracting representative spectral information from bi-temporal images; and 3) high stability and accuracy for identifying both sparse sporadic changing pixels and large changing areas whilst preserving the edges. Comprehensive experiments on three publicly available datasets have fully validated the efficacy and efficiency of the proposed methodology.

Mobile application developers sometimes might not be serious about source code security and publish apps to the marketplaces. Therefore, it is essential to have a fully automated security solutions generator to integrate security-by-design into the development practices, especially for the Android platform. This research proposes a Machine Learning (ML) based highly accurate method to detect Android source code vulnerabilities. A new labelled dataset containing Android source code vulnerability samples was generated initially. The dataset was used to train binary and multi-class classification based ML models, to identify code issues by following a static analysis approach. The proposed model can detect code vulnerabilities with a 0.90 F1-Score and vulnerability categories (CWE) with a 0.96 F1-Score. By integrating this with the Android development environment, app developers can analyse source code and identify security vulnerabilities in real-time. The proposed framework can be extended to suggest suitable patches to overcome the source code issues by providing real-time fixes in future.

Tabular synthetic data generating models based on Generative Adversarial Network (GAN) show significant contributions to enhancing the performance of deep learning models by providing a sufficient amount of training data. However, the existing GAN-based models cannot preserve the feature correlations in synthetic data during the data synthesis process. Therefore, the synthetic data become unrealistic and creates a problem for certain applications like correlation-based feature weighting. In this short theoretical paper, we showed a promising approach based on the topology of datasets to preserve correlation in synthetic data. We formulated our hypothesis for preserving correlation in synthetic data and used persistent homology to show that the topological spaces of the original and synthetic data have dissimilarity in topological features, especially in 0thand 1stHomology groups. Finally, we concluded that minimizing the difference in topological features can make the synthetic data space locally homeomorphic to the original data space, and the synthetic data may preserve the feature correlation under homeomorphism conditions.

The integration of the IoT network with the Operational Technology (OT) network is increasing rapidly. However, this incorporation of IoT devices into the OT network makes the industrial control system vulnerable to various cyber threats. Hacking an IoT device at the network edge, an attacker can move laterally to compromise the main control server and manipulate the whole control system of the industrial infrastructure. In this paper, we have proposed an automated Micro-segmentation (MS) model based on Machine Learning (ML) algorithms to reduce the lateral movement of an attacker or malware. The proposed model generates the micro-segments based on network traffic and blocks the malicious traffic at each segment. We have taken UNSW-NB15 and IoTID20 datasets for our experiments. Experimental results show that after generating micro-segments and separating the normal traffic, the model limits redundant links and blocks malicious traffic. Limiting the usage of redundant links reduces the lateral movement or spreading of malware. We also considered the deterministic epidemic model to analyze the device infection rate due to lateral movement or malware propagation.

Imbalanced classes in datasets are common problems often found in security data. Therefore, several strategies like class resampling and cost-sensitive training have been proposed to address it. In this paper, we propose a data augmentation strategy to oversample the minority classes in the dataset. Using our Sort-Augment-Combine (SAC) technique, we split the dataset into subsets of the class labels and then generate synthetic data from each of the subsets. The synthetic data were then used to oversample the minority classes. Upon the completion of the oversampling, the independent classes were combined to form an augmented training data for model fitting. Using performance metrics such as accuracy, recall (sensitivity) and true positives (specificity), the models trained using the augmented datasets show an improvement in performance metrics over the original dataset. Similarly, in a binary class dataset, SAC performed optimally and the combination of SAC and ROSE model shows an improvement in overall accuracy, sensitivity and specificity when compared with the performance of the Random Forest model on the original dataset, ROSE and SMOTE augmented datasets.

Industrial Control Systems are essential to managing national critical infrastructure, yet the security of these systems historically relies on isolation. The adoption of modern software solutions, and the unique challenges presented by legacy systems, has made securing industrial networks increasingly difficult. With malware identified as the leading cause of cyber incident in industrial systems, this work presents a comparative study of existing malware detection techniques, to compare both accuracy and suitability for use in the defence of industrial systems.

The operational cyber-physical system (CPS) state, safety and resource availability is impacted by the safety and security measures in place. This paper focused on i) command injection (CI) attack that alters the system behaviour through injection of false control and configuration commands into a control system and ii) response injection (RI) attacks that modifies the response from server to client, thereby providing false information about system state. In this project, we implemented deep learning (DL) multi-layered security model approach for securing industrial control system (ICS) against malicious CI and RI attacks. We validated this approach with two case studies: i) network transactions between a Remote Terminal Unit (RTU) and a Master Control Unit (MTU) in-house SCADA gas pipeline control system and ii) a case study of command and response injection attacks. Based on this project result, we show that the proposed approach achieved a significant attacks detection capability of 96.50%. Also, demonstrated that performance of attack detection techniques applied can be influences by the nature of network transactions with respect to the domain of application. Hence, robustness and resilience of operational CPS state and performance are influenced by the safety and security measures in place which is specific to the CPS device in question.

This paper looks at potential vulnerabilities of the Smart Grid energy infrastructure to data injection cyber-attacks and the means of addressing these vulnerabilities through intelligent data analysis. Efforts are being made by multiple groups to provide to defence-in-depth to Smart Grid systems by developing attack detection algorithms utilising artificial neural networks that evaluate data communication between system components. The first priority of such algorithms is the detection of anomalous commands or data states; however, anomalous data states may also result from physical situations legitimately encountered by equipment. This work aims at not only detecting and alerting on anomalies, but at intelligent learning of the system behaviour to distinguish between malicious interference and anomalous system states occurring due to maintenance activity or natural phenomena, such as for instance a nearby lightning strike causing a short-circuit fault.

Advanced Persistent Threats (APTs) have been a major challenge in securing both Information Technology (IT) and Operational Technology (OT) systems. Due to their capability to navigates around defenses and to evade detection for a prolonged period of time, targeted APT attacks present an increasing concern for both cyber security and business continuity personnel. This paper explores the application of Artificial Immune System (AIS) and Recurrent Neural Networks (RNNs) variants for APT detection. It has been shown that the variants of the suggested algorithms provide not only detection capability, but can also classify malicious data traffic with respect to the type of APT attacks.

To manage uncertainty in reservoir development projects, the Value of Information is one of the main factors on which the decision is based to determine whether it is necessary to acquire additional data. However, subsurface data is not always precise and is characterized by a certain level of fuzziness. In this paper, a model is formulated to assess the Value of Information in the oil and gas industry in cases where the data proposed to be acquired is imprecise. The methodology is based on the use of fuzzy data modelling and analysis aimed at providing decision support for oil field developers. An oilfield from North Africa is used as a case study to show how the methodology works. This work shows how the analysis can be utilized to reach financial decisions on the necessity of additional data acquisition.

The need for computer-assisted real-time anomaly detection in engineering data used for condition monitoring is apparent in various applications, including the oil and gas, automotive industries and many other engineering domains. To reduce the reliance on domain-specific experts' knowledge, this paper proposes a deep learning framework that can assist in building a versatile anomaly detection tool needed for effective condition monitoring. The framework enables building a computational anomaly detection model using different types of neural networks and supervised learning. While building such a model, three types of ANN units were compared: a recurrent neural network, a long short-term memory network, and a gated recurrent unit. Each of these units has been evaluated on two benchmark public datasets. The experimental results of this comparative study revealed that the LSTM network unit that uses the sigmoid activation function, the Mean Absolute Error as the objective Loss function and the Adam optimizer as the output layer showed the best performance and attained the accuracy of over 77 % in detecting anomalous values in the datasets. Having determined the best performing combination of the neural network components, a computational anomaly detection model was built within the framework, which was successfully evaluated on real-life engineering datasets comprising the timeseries datasets from an offshore installation in North Sea and another dataset from the automotive industry, which enabled exploring the anomaly classification capability of the proposed framework.

The recent growth of the Internet of Things (IoT) has resulted in a rise in IoT based DDoS attacks. This paper presents a solution to the detection of botnet activity within consumer IoT devices and networks. A novel application of Deep Learning is used to develop a detection model based on a Bidirectional Long Short Term Memory based Recurrent Neural Network (BLSTM-RNN). Word Embedding is used for text recognition and conversion of attack packets into tokenised integer format. The developed BLSTM-RNN detection model is compared to a LSTM-RNN for detecting four attack vectors used by the mirai botnet, and evaluated for accuracy and loss. The paper demonstrates that although the bidirectional approach adds overhead to each epoch and increases processing time, it proves to be a better progressive model over time. A labelled dataset was generated as part of this research, and is available upon request.

A multitenant cloud-application that is designed to use several components needs to implement the required degree of isolation between the components when the workload changes. The highest degree of isolation results in high resource consumption and running cost per component. A low degree of isolation allows sharing of resources, but leads to degradation in performance and to increased security vulnerability. This paper presents a simulation-based approach operating on computational metaheuristics that search for optimal ways of deploying components of a cloud-hosted application to guarantee multitenancy isolation When the workload changes, an open multiclass Queuing Network model is used to determine the average number of component access requests, followed by a metaheuristic search for the optimal deployment solutions of the components in question. The simulation-based evaluation of optimization performance showed that the solutions obtained were very close to the target solution. Various recommendations and best practice guidelines for deploying components in a way that guarantees the required degree of isolation are also provided.

Mobile activity recognition from sensor data is based on supervised learning algorithms. Many algorithms have been proposed for this task. One of such algorithms is the K-nearest neighbour (KNN) algorithm. However, since KNN is an instance based algorithm its use in mobile activity recognition has been limited to offline evaluation on collected data. This is because for KNN to work well all the training instances must be kept in memory for similarity measurement with the test instance. This is however prohibitive for mobile environment. Therefore, we propose an unsupervised learning step that reduces the training set to a proportional size of the original dataset. The novel approach applies clustering to the dataset to obtain a set of micro clusters from which cluster characteristics are extracted for similarity measurement with new unseen data. These reduced representative sets can be used for classifying new instances using the nearest neighbour algorithm step on the mobile phone. Experimental evaluation of our proposed approach using real mobile activity recognition dataset shows improved result over the basic KNN algorithm.

An adaptive multi-tiered framework, which can be utilised for designing a context-aware cyber physical system is proposed in the paper and is applied within the context of providing data availability by monitoring electromagnetic interference. The adaptability is achieved through the combined use of statistical analysis and computational intelligence techniques. The proposed framework has the generality to be applied across a wide range of problem domains requiring processing, analysis and interpretation of data obtained from heterogeneous resources.

An adaptive inferential measurement framework for control and automation systems has been proposed in the paper and tested on simulated traffic surveillance data. The use of the framework enables making inferences related to the presence of anomalies in the surveillance data with the help of statistical, computational and clustering analysis. Moreover, the performance of the ensemble of these tools can be dynamically tuned by a computational intelligence technique. The experimental results have demonstrated that the framework is generally applicable to various problem domains and reasonable performance is achieved in terms of inferential accuracy. Computational intelligence can also be effectively utilised for identifying the main contributing features in detecting anomalous data points within the surveillance data.

This paper investigates the use of computational intelligence (CI) techniques, alongside mathematical and statistical models, to effectively assess the state and conditions of subsea controls systems from sensor data. The main focus of the work is to apply the CI techniques to the process of fault detection and identification (FDI) by developing a generic framework capable of performing the FDI activities pro-actively and in real-time. The proposed framework has been implemented and evaluated on two experimental datasets, demonstrating the viability and benefits of the suggested approach to adaptive fault detection.

This paper improves a recently developed multi-objective particle swarm optimizer (D2MOPSO) that incorporates dominance with decomposition used in the context of multi-objective optimization. Decomposition simplifies a multi-objective problem (MOP) by transforming it to a set of aggregation problems, whereas dominance plays a major role in building the leaders' archive. D2MOPSO introduces a new archiving technique that facilitates attaining better diversity and coverage in both objective and solution spaces. The improved method is evaluated on standard benchmarks including both constrained and unconstrained test problems, by comparing it with three state of the art multi-objective evolutionary algorithms: MOEA/D, OMOPSO, and dMOPSO. The comparison and analysis of the experimental results, supported by statistical tests, indicate that the proposed algorithm is highly competitive, efficient, and applicable to a wide range of multi-objective optimization problems.

A novel presentation for channel selection problem in Brain-Computer Interfaces (BCI) is introduced here. Continuous presentation in a projected two-dimensional space of the Electroencephalograph (EEG) cap is proposed. A multi-objective particle swarm optimization method (D2MOPSO) is employed where particles move in the EEG cap space to locate the optimum set of solutions that minimize the number of selected channels and the classification error rate. This representation focuses on the local relationships among EEG channels as the physical location of the channels is explicitly represented in the search space avoiding picking up channels that are known to be uncorrelated with the mental task. In addition continuous presentation is a more natural way for problem solving in PSO framework. The method is validated on 10 subjects performing right-vs-left motor imagery BCI. The results are compared to these obtained using Sequential Floating Forward Search (SFFS) and shows significant enhancement in classification accuracy but most importantly in the distribution of the selected channels.

This paper addresses the problem of maintaining the reliability of power grid. It examines the present models and policies used in estimating equipment life-time and maintenance scheduling, and suggests possible improvements resulted from applying the methods of computational intelligence - fuzzy inference in particular in relation to identification and diagnosis of electrical equipment faults. The suggested methodology is based on intelligent sensing and modern data communication technologies built as a smart layer on top of the existing grid infrastructure. The main benefits of the suggested approach are the reduction of equipment downtime, improvement of diagnostic capabilities within the grid, and the reduction of maintenance cost.

The operation of drilling rigs is highly expensive. It is therefore important to be able to identify and analyse factors affecting rig operations. We investigate the use of two Genetic Algorithms, K2GA and ChainGA, to induce a Bayesian Network model for the real world problem of Rig Operations Management. We sample from a unique dataset derived from the commercial market intelligence databases assembled by ODS-Petrodata Ltd. We observe a trade-off between K2GA, which finds significantly better scoring networks on our dataset, and ChainGA, which uses only one quarter of the computation time. We analyse the best structures produced from an industry standpoint and conclude by outlining a few potential applications of the models to support rig operations.

Chemotherapy treatment for cancer is a complex optimisation problem with a large number of interacting variables and constraints. A number of different heuristics have been applied to it with varying success. In this paper we expand on this by applying two estimation of distribution algorithms to the problem. One is UMDA and the other is hBOA, the first EDA using a multivariate probabilistic model to be applied to the chemotherapy problem. While instinct would lead us to predict that the more sophisticated algorithm would yield better performance on a complex problem like this, we show that it is outperformed by the algorithms using the simpler univariate model. We hypothesise that this is caused by the more sophisticated algorithm being impeded by the large number of interactions in the problem which though present, do not complicate the search for optima.

This paper presents a methodology for using heuristic search methods to optimise cancer chemotherapy. Specifically, two evolutionary algorithms- Population Based Incremental Learning (PBIL), which is an Estimation of Distribution Algorithm (EDA), and Genetic Algorithms (GAs) have been applied to the problem of finding effective chemotherapeutic treatments. To our knowledge, EDAs have been applied to fewer real world problems compared to GAs, and the aim of the present paper is to expand the application domain of this technique. We compare and analyse the performance of both algorithms and draw a conclusion as to which approach to cancer chemotherapy optimisation is more efficient and helpful in the decision-making activity led by the oncologists. Categories and Subject Descriptors

This paper presents a practical methodology of improving the efficiency of genetic algorithms through tuning the factors significantly affecting GA performance. This methodology is based on the methods of statistical inference and has been successfully applied to both binary-and integer-encoded genetic algorithms that search for good chemotherapeutic schedules