Breaching Subjects' Thoughts Privacy: A Study with Visual Stimuli and Brain-Computer Interfaces.

Brain-computer interfaces (BCIs) started being used in clinical scenarios, reaching nowadays new fields such as entertainment or learning. Using BCIs, neuronal activity can be monitored for various purposes, with the study of the central nervous system response to certain stimuli being one of them, being the case of evoked potentials. However, due to the sensitivity of these data, the transmissions must be protected, with blockchain being an interesting approach to ensure the integrity of the data. This work focuses on the visual sense, and its relationship with the P300 evoked potential, where several open challenges related to the privacy of subjects' information and thoughts appear when using BCI. The first and most important challenge is whether it would be possible to extract sensitive information from evoked potentials. This aspect becomes even more challenging and dangerous if the stimuli are generated when the subject is not aware or conscious that they have occurred. There is an important gap in this regard in the literature, with only one work existing dealing with subliminal stimuli and BCI and having an unclear methodology and experiment setup. As a contribution of this paper, a series of experiments, five in total, have been created to study the impact of visual stimuli on the brain tangibly. These experiments have been applied to a heterogeneous group of ten subjects. The experiments show familiar visual stimuli and gradually reduce the sampling time of known images, from supraliminal to subliminal. The study showed that supraliminal visual stimuli produced P300 potentials about 50% of the time on average across all subjects. Reducing the sample time between images degraded the attack, while the impact of subliminal stimuli was not confirmed. Additionally, younger subjects generally presented a shorter response latency. This work corroborates that subjects' sensitive data can be extracted using visual stimuli and P300.

S3: An AI-Enabled User Continuous Authentication for Smartphones Based on Sensors, Statistics and Speaker Information.

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.

Twitter social bots: The 2019 Spanish general election data.

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.

BEHACOM - a dataset modelling users' behaviour in computers.

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.

A Scalable Architecture for the Dynamic Deployment of Multimodal Learning Analytics Applications in Smart Classrooms.

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.

PALOT: Profiling and Authenticating Users Leveraging Internet of Things.

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.

Intelligent and Dynamic Ransomware Spread Detection and Mitigation in Integrated Clinical Environments.

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.

Improving the Security and QoE in Mobile Devices through an Intelligent and Adaptive Continuous Authentication System.

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.