Search

Autism is a developmental condition that affects motor skill development. There is a lack of comprehensive research exploring the potential benefits of extended reality (XR) technologies, including virtual reality (VR) and augmented reality (AR), for improving motor skills in autistic children. This systematic literature review (SLR) addresses this research gap by investigating XR-based interventions targeting motor skill development in autistic children. The SLR analysed 15 primary studies published between 2012 and 2024, examining the use of VR and AR to improve motor skill development in autistic children. The interventions ranged from one session to 12 weeks, lasting 12 to 45 minutes, and targeted various body movements. XR platforms and devices used included VR headsets, motion capture systems, and exercise bikes. Recurrent neural networks, dynamic difficulty adjustment, and behaviour trees were employed to enhance intervention dynamics and extract valuable insights from collected data. The results suggest that using XR interventions has significant potential to improve physical activity levels and motor skills development among autistic children. However, the research designs varied, with only one study including their intervention framework’s generalisation and maintenance phases. This study offers an encouraging avenue for future research and intervention design in this field.

Anomaly Detection systems based on Machine and Deep learning are the most promising solutions to detect cyberattacks in the industry. However, these techniques are vulnerable to adversarial attacks that downgrade prediction performance. Several techniques have been proposed to measure the robustness of Anomaly Detection in the literature. However, they do not consider that, although a small perturbation in an anomalous sample belonging to an attack, i.e., Denial of Service, could cause it to be misclassified as normal while retaining its ability to damage, an excessive perturbation might also transform it into a truly normal sample, with no real impact on the industrial system. This paper presents a methodology to calculate the robustness of Anomaly Detection models in industrial scenarios. The methodology comprises four steps and uses a set of additional models called support models to determine if an adversarial sample remains anomalous. We carried out the validation using the Tennessee Eastman process, a simulated testbed of a chemical process. In such a scenario, we applied the methodology to both a Long-Short Term Memory (LSTM) neural network and 1-dimensional Convolutional Neural Network (1D-CNN) focused on detecting anomalies produced by different cyberattacks. The experiments showed that 1D-CNN is significantly more robust than LSTM for our testbed. Specifically, a perturbation of 60% (empirical robustness of 0.6) of the original sample is needed to generate adversarial samples for LSTM, whereas in 1D-CNN the perturbation required increases up to 111% (empirical robustness of 1.11).

Brain-Computer Interfaces (BCI) arose as systems that merge computing systems with the human brain to facilitate recording, stimulation, and inhibition of neural activity. Over the years, the development of BCI technologies has shifted towards miniaturization of devices that can be seamlessly embedded into the brain and can target single neuron or small population sensing and control. We present a motivating example highlighting vulnerabilities of two promising micron-scale BCI technologies, demonstrating the lack of security and privacy principles in existing solutions. This situation opens the door to a novel family of cyberattacks, called neuronal cyberattacks, affecting neuronal signaling. This article defines the first two neural cyberattacks, Neuronal Flooding (FLO) and Neuronal Scanning (SCA), where each threat can affect the natural activity of neurons. This work implements these attacks in a neuronal simulator to determine their impact over the spontaneous neuronal behavior, defining three metrics: number of spikes, percentage of shifts, and dispersion of spikes. Several experiments demonstrate that both cyberattacks produce a reduction of spikes compared to spontaneous behavior, generating a rise in temporal shifts and a dispersion increase. Mainly, SCA presents a higher impact than FLO in the metrics focused on the number of spikes and dispersion, where FLO is slightly more damaging, considering the percentage of shifts. Nevertheless, the intrinsic behavior of each attack generates a differentiation on how they alter neuronal signaling. FLO is adequate to generate an immediate impact on the neuronal activity, whereas SCA presents higher effectiveness for damages to the neural signaling in the long-term.

In recent decades, Industrial Control Systems (ICS) have been affected by heterogeneous cyberattacks that have a huge impact on the physical world and the people's safety. Nowadays, the techniques achieving the best performance in the detection of cyber anomalies are based on Machine Learning and, more recently, Deep Learning. Due to the incipient stage of cybersecurity research in ICS, the availability of datasets enabling the evaluation of anomaly detection techniques is insufficient. In this paper, we propose a methodology to generate reliable anomaly detection datasets in ICS that consists of four steps: attacks selection, attacks deployment, traffic capture and features computation. The proposed methodology has been used to generate the Electra Dataset, whose main goal is the evaluation of cybersecurity techniques in an electric traction substation used in the railway industry. Using the Electra dataset, we train several Machine Learning and Deep Learning models to detect anomalies in ICS and the performed experiments show that the models have high precision and, therefore, demonstrate the suitability of our dataset for use in production systems.

Federated Learning (FL) has emerged as a promising approach to address privacy concerns inherent in Machine Learning (ML) practices. However, conventional FL methods, particularly those following the Centralized FL (CFL) paradigm, utilize a central server for global aggregation, which exhibits limitations such as bottleneck and single point of failure. To address these issues, the Decentralized FL (DFL) paradigm has been proposed, which removes the client–server boundary and enables all participants to engage in model training and aggregation tasks. Nevertheless, as CFL, DFL remains vulnerable to adversarial attacks, notably poisoning attacks that undermine model performance. While existing research on model robustness has predominantly focused on CFL, there is a noteworthy gap in understanding the model robustness of the DFL paradigm. In this paper, a thorough review of poisoning attacks targeting the model robustness in DFL systems, as well as their corresponding countermeasures, are presented. Additionally, a solution called DART is proposed to evaluate the robustness of DFL models, which is implemented and integrated into a DFL platform. Through extensive experiments, this paper compares the behavior of CFL and DFL under diverse poisoning attacks, pinpointing key factors affecting attack spread and effectiveness within the DFL. It also evaluates the performance of different defense mechanisms and investigates whether defense mechanisms designed for CFL are compatible with DFL. The empirical results provide insights into research challenges and suggest ways to improve the robustness of DFL models for future research.

Abstract When detecting cyberattacks in Industrial settings, it is not sufficient to determine whether the system is suffering a cyberattack. It is also fundamental to explain why the system is under a cyberattack and which are the assets affected. In this context, the Anomaly Detection based on Machine Learning (ML) and Deep Learning (DL) techniques showed great performance when detecting cyberattacks in industrial scenarios. However, two main limitations hinder using them in a real environment. Firstly, most solutions are trained using a supervised approach, which is impractical in the real industrial world. Secondly, the use of black‐box ML and DL techniques makes it impossible to interpret the decision made by the model. This article proposes an interpretable and semi‐supervised system to detect cyberattacks in Industrial settings. Besides, our proposal was validated using data collected from the Tennessee Eastman Process. To the best of our knowledge, this system is the only one that offers interpretability together with a semi‐supervised approach in an industrial setting. Our system discriminates between causes and effects of anomalies and also achieved the best performance for 11 types of anomalies out of 20 with an overall recall of 0.9577, a precision of 0.9977, and a F1‐score of 0.9711.

The term social bots refer to software-controlled accounts that actively participate in the social platforms to influence public opinion toward desired directions. To this extent, this data descriptor presents a Twitter dataset collected from October 4th to November 11th, 2019, within the context of the Spanish general election. Starting from 46 hashtags, the collection contains almost eight hundred thousand users involved in political discussions, with a total of 5.8 million tweets. The proposed data descriptor is related to the research article available at [1]. Its main objectives are: i) to enable worldwide researchers to improve the data gathering, organization, and preprocessing phases; ii) to test machine-learning-powered proposals; and, finally, iii) to improve state-of-the-art solutions on social bots detection, analysis, and classification. Note that the data are anonymized to preserve the privacy of the users. Throughout our analysis, we enriched the collected data with meaningful features in addition to the ones provided by Twitter. In particular, the tweets collection presents the tweets’ topic mentions and keywords (in the form of political bag-of-words), and the sentiment score. The users’ collection includes one field indicating the likelihood of one account being a bot. Furthermore, for those accounts classified as bots, it also includes a score that indicates the affinity to a political party and the followers/followings list.

This paper details the methodology and approach conducted to monitor the behaviour of twelve users interacting with their computers for fifty-five consecutive days without preestablished indications or restrictions. The generated dataset, called BEHACOM, contains for each user a set of features that models, in one-minute time windows, the usage of computer resources such as CPU or memory, as well as the activities registered by applications, mouse and keyboard. It has to be stated that the collected data have been treated in a privacy-preserving way during each phase of the collection and analysis. Together with the features and their explanation, we also detail the software used to gather and process the data. Finally, this article describes the data distribution of the BEHACOM dataset.

Continuous authentication systems have been proposed as a promising solution to authenticate users in smartphones in a non-intrusive way. However, current systems have important weaknesses related to the amount of data or time needed to build precise user profiles, together with high rates of false alerts. Voice is a powerful dimension for identifying subjects but its suitability and importance have not been deeply analyzed regarding its inclusion in continuous authentication systems. This work presents the S3 platform, an artificial intelligence-enabled continuous authentication system that combines data from sensors, applications statistics and voice to authenticate users in smartphones. Experiments have tested the relevance of each kind of data, explored different strategies to combine them, and determined how many days of training are needed to obtain good enough profiles. Results showed that voice is much more relevant than sensors and applications statistics when building a precise authenticating system, and the combination of individual models was the best strategy. Finally, the S3 platform reached a good performance with only five days of use available for training the users’ profiles. As an additional contribution, a dataset with 21 volunteers interacting freely with their smartphones for more than sixty days has been created and made available to the community.

Web platforms are gaining relevance in eHealth, where they ease the interaction between patients and clinician. However, some clinical fields, such as the cardiovascular one, still need more effort because cardiovascular diseases are the principal cause of death and medical resources expenditure worldwide. The lack of daily control is the main reason hypertension is a current health problem, and medical web services could improve this situation. To face this challenge, this work proposes a novel intelligent web-based ecosystem, called SENIOR, capable of predicting adverse blood pressure events. The innovation of the SENIOR ecosystem relies on a wearable device measuring patient’s biomarkers such as blood pressure, a mobile application acquiring patient’s information, and a web platform consulting environmental services, processing data, and predicting blood pressure. The second contribution of this work is to consider novel environmental features based on the users’ location, such as climate and pollution data, to increase the knowledge about known variables affecting hypertension. Finally, our last contribution is a proof of concept with several machine learning algorithms predicting blood pressure values both in real-time and future temporal windows within one day has demonstrated the suitability of SENIOR.

Industrial Control Systems (ICSs) are widely used in critical infrastructures to support the essential services of society. Therefore, their protection against terrorist activities, natural disasters, and cyber threats is critical. Diverse cyber attack detection systems have been proposed over the years, in which each proposal has applied different steps and methods. However, there is a significant gap in the literature regarding methodologies to detect cyber attacks in ICS scenarios. The lack of such methodologies prevents researchers from being able to accurately compare proposals and results. In this work, we present a Methodology for Anomaly Detection in Industrial Control Systems (MADICS) to detect cyber attacks in ICS scenarios, which is intended to provide a guideline for future works in the field. MADICS is based on a semi-supervised anomaly detection paradigm and makes use of deep learning algorithms to model ICS behaviors. It consists of five main steps, focused on pre-processing the dataset to be used with the machine learning and deep learning algorithms; performing feature filtering to remove those features that do not meet the requirements; feature extraction processes to obtain higher order features; selecting, fine-tuning, and training the most appropriate model; and validating the model performance. In order to validate MADICS, we used the popular Secure Water Treatment (SWaT) dataset, which was collected from a fully operational water treatment plant. The experiments demonstrate that, using MADICS, we can achieve a state-of-the-art precision of 0.984 (as well as a recall of 0.750 and F1-score of 0.851), which is above the average of other works, proving that the proposed methodology is suitable for use in real ICS scenarios.

The smart classrooms of the future will use different software, devices and wearables as an integral part of the learning process. These educational applications generate a large amount of data from different sources. The area of Multimodal Learning Analytics (MMLA) explores the affordances of processing these heterogeneous data to understand and improve both learning and the context where it occurs. However, a review of different MMLA studies highlighted that ad-hoc and rigid architectures cannot be scaled up to real contexts. In this work, we propose a novel MMLA architecture that builds on software-defined networks and network function virtualization principles. We exemplify how this architecture can solve some of the detected challenges to deploy, dismantle and reconfigure the MMLA applications in a scalable way. Additionally, through some experiments, we demonstrate the feasibility and performance of our architecture when different classroom devices are reconfigured with diverse learning tools. These findings and the proposed architecture can be useful for other researchers in the area of MMLA and educational technologies envisioning the future of smart classrooms. Future work should aim to deploy this architecture in real educational scenarios with MMLA applications.

Continuous authentication was introduced to propose novel mechanisms to validate users’ identity and address the problems and limitations exposed by traditional techniques. However, this methodology poses several challenges that remain unsolved. In this paper, we present a novel framework, PALOT, that leverages IoT to provide context-aware, continuous and non-intrusive authentication and authorization services. To this end, we propose a formal information system model based on ontologies, representing the main source of knowledge of our framework. Furthermore, to recognize users’ behavioral patterns within the IoT ecosystem, we introduced a new module called “confidence manager”. The module is then integrated into an extended version of our early framework architecture, IoTCAF, which is consequently adapted to include the above-mentioned component. Exhaustive experiments demonstrated the efficacy, feasibility and scalability of the proposed solution.

Medical Cyber-Physical Systems (MCPS) hold the promise of reducing human errors and optimizing healthcare by delivering new ways to monitor, diagnose and treat patients through integrated clinical environments (ICE). Despite the benefits provided by MCPS, many of the ICE medical devices have not been designed to satisfy cybersecurity requirements and, consequently, are vulnerable to recent attacks. Nowadays, ransomware attacks account for 85% of all malware in healthcare, and more than 70% of attacks confirmed data disclosure. With the goal of improving this situation, the main contribution of this paper is an automatic, intelligent and real-time system to detect, classify, and mitigate ransomware in ICE. The proposed solution is fully integrated with the ICE++ architecture, our previous work, and makes use of Machine Learning (ML) techniques to detect and classify the spreading phase of ransomware attacks affecting ICE. Additionally, Network Function Virtualization (NFV) and Software Defined Networking (SDN)paradigms are considered to mitigate the ransomware spreading by isolating and replacing infected devices. Different experiments returned a precision/recall of 92.32%/99.97% in anomaly detection, an accuracy of 99.99% in ransomware classification, and promising detection and mitigation times. Finally, different labelled ransomware datasets in ICE have been created and made publicly available.

Continuous authentication systems for mobile devices focus on identifying users according to their behaviour patterns when they interact with mobile devices. Among the benefits provided by these systems, we highlight the enhancement of the system security, having permanently authenticated the users; and the improvement of the users’ quality of experience, minimising the use of authentication credentials. Despite the benefits of these systems, they also have open challenges such as the authentication accuracy and the adaptability to new users’ behaviours. Continuous authentication systems should manage these challenges without forgetting critical aspects of mobile devices such as battery consumption, computational limitations and response time. With the goal of improving these previous challenges, the main contribution of this paper is the design and implementation of an intelligent and adaptive continuous authentication system for mobile devices. The proposed system enables the real-time users’ authentication by considering statistical information from applications, sensors and Machine Learning techniques based on anomaly detection. Several experiments demonstrated the accuracy, adaptability, and resources consumption of our solution. Finally, its utility is validated through the design and implementation of an online bank application as proof of concept, which allows users to perform different actions according to their authentication level.