Pasar al contenido principal

DETECCION TEMPRANA DE INTRUSIONES Y ANOMALIAS EN REDES DEFINIDAS POR SOFTWARE

PID2019-111388GB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2019
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDADE DA CORUÑA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 15
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Measuring Early Detection of Anomalies

  • López-Vizcaíno, Manuel F.
  • Nóvoa, Francisco
  • Fernández, Diego
  • Cacheda, Fidel
[Abstract] Early detection is a matter of growing importance in multiple domains as network security, health conditions over social network services or weather forecasts related disasters. It is not enough to make a good decision but it also needs to be made on time. In this paper, we define a method to evaluate detection of anomalies in time-aware systems. To do so, we present the early detection problem from a generic perspective, examine the evaluation metrics available and propose a new metric, named TaP (Time aware Precision). A set of experiments using three different datasets from different fields are performed in order to compare the behaviour of the different metrics. Two different approaches were followed, first a batch evaluation is performed, followed by a streaming evaluation which allows to present a more realistic behaviour of the systems. For both steps, we propose two sets of experiments. The first one using baseline models, followed by the evaluation of a set of Machine Learning algorithms results. The presented metric allows the amount of items needed to take a decision to be taken into account, not depending on the specific dataset but on the nature of the problem to solve., Xunta de Galicia; ED431G 2019/01, This work was supported in part by the Ministry of Economy and Competitiveness of Spain and Fondo Europeo de Desarrollo Regional (FEDER) Funds of the European Union under Project PID2019-111388GB-I00; and in part by the Centro de Investigación de Galicia-Centro de Investigación en Tecnologías de la Información y las Comunicaciones (CITIC) Funded by Xunta de Galicia and the European Union (European Regional Development Fund-Galicia 2014-2020 Program), under Grant ED431G 2019/01.
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

AI-Based User Authentication Reinforcement by Continuous Extraction of Behavioral Interaction Features

  • Garabato, D.
  • Dafonte, Carlos
  • Santoveña, Raúl
  • Silvelo, Arturo
  • Nóvoa, Francisco
  • Manteiga, Minia
Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature., [Abstract]: In this work, we conduct an experiment to analyze the feasibility of a continuous authentication method based on the monitorization of the users' activity to verify their identities through specific user profiles modeled via Artificial Intelligence techniques. In order to conduct the experiment, a custom application was developed to gather user records in a guided scenario where some predefined actions must be completed. This dataset has been anonymized and will be available to the community. Additionally, a public dataset was also used for benchmarking purposes so that our techniques could be validated in a non-guided scenario. Such data were processed to extract a number of key features that could be used to train three different Artificial Intelligence techniques: Support Vector Machines, Multi-Layer Perceptrons, and a Deep Learning approach. These techniques demonstrated to perform well in both scenarios, being able to authenticate users in an effective manner. Finally, a rejection test was conducted, and a continuous authentication system was proposed and tested using weighted sliding windows, so that an impostor could be detected in a real environment when a legitimate user session is hijacked., Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED431B 2021/36, Xunta de Galicia; ED481A-2019/155, This work made use of the infrastructures acquired with Grants provided by the State Research Agency (AEI) of the Spanish Government and the European Regional Development Fund (FEDER), through RTI2018-095076-B-C22, and PID2019-525 111388GB-I00. We acknowledge support from CIGUS-CITIC, funded by Xunta de Galicia and the European Union (FEDER Galicia 2014-2020 Program) through Grant ED431G 2019/01; research consolidation Grant ED431B 2021/36; Art.83 collaboration F19/03 with the enterprise Odeene S.L.; and scholarship from Xunta de Galicia and the European Union (European Social Fund - ESF) ED481A-2019/155.
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Annotated Dataset for Anomaly Detection in a Data Center with IoT Sensors

  • Vigoya, Laura
  • Fernández, Diego
  • Carneiro, Víctor
  • Cacheda, Fidel
[Abstract] The relative simplicity of IoT networks extends service vulnerabilities and possibilities to different network failures exhibiting system weaknesses. Therefore, having a dataset with a sufficient number of samples, labeled and with a systematic analysis, is essential in order to understand how these networks behave and detect traffic anomalies. This work presents DAD: a complete and labeled IoT dataset containing a reproduction of certain real-world behaviors as seen from the network. To approximate the dataset to a real environment, the data were obtained from a physical data center, with temperature sensors based on NFC smart passive sensor technology. Having carried out different approaches, performing mathematical modeling using time series was finally chosen. The virtual infrastructure necessary for the creation of the dataset is formed by five virtual machines, a MQTT broker and four client nodes, each of them with four sensors of the refrigeration units connected to the internal IoT network. DAD presents a seven day network activity with three types of anomalies: duplication, interception and modification on the MQTT message, spread over 5 days. Finally, a feature description is performed, so it can be used for the application of the various techniques of prediction or automatic classification., This project was funded by the Accreditation, Structuring, and Improvement of Consolidated Research Units and Singular Centers (ED431G/01), funded by Vocational Training of the Xunta de Galicia endowed with EU FEDER funds. This research was partially supported by the Ministry of Science and Innovation, Spain’s National Research and Development Plan, through the PID2019-111388GB-I00 project, Xunta de Galicia; ED431G/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Low Cost Automated Security Audit System

  • Fernández-Arruti Gallego, Pedro
  • Estévez Pereira, Julio Jairo
  • Nóvoa, Francisco
  • Dafonte, Carlos
  • Fernández, Diego
Presented at the 4th XoveTIC Conference, A Coruña, Spain, 7–8 October 2021., [Abstract] In recent years, a quick transition towards digitization has been observed in most organizations. Along with it, certain inherent problems have appeared, such as the increase in cyber threats. Large organizations are able to adapt easily, but this does not happen with small and medium-sized companies. Currently, there are very few solutions aimed at fulfilling the needs of these small enterprises, so we have worked on a tool for them. Our tool is capable of displaying key, easy-to-interpret information related to each organization’s network assets. To achieve this, we used passive and active analysis techniques and successfully evaluated the viability of using machine learning techniques to get more meaningful information. All of the information obtained is displayed in a simple web application, which is designed to be used by managers in organizations without them needing to handle complex concepts and vocabulary., CITIC, as a Research Center accredited by the Galician University System, is funded by “Consellería de Cultura, Educación e Universidade from Xunta de Galicia”, supported in an 80% through ERDF, ERDF Operational Programme Galicia 2014–2020, and the remaining 20% by “Secretaría Xeral de Universidades (Grant ED431G 2019/01). This work was also funded by the research consolidation grant ED431B 2021/36, Art.83 collaboration F19/17, the Ministry of Economy and Competitiveness of Spain, and the FEDER funds of the European Union (Project PID2019-111388GB-I00), Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED431B 2021/36
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Time Aware F-Score for Cybersecurity Early Detection Evaluation

  • López-Vizcaíno, Manuel F.
  • Nóvoa, Francisco
  • Fernández, Diego
  • Cacheda, Fidel
[Abstract]: With the increase in the use of Internet interconnected systems, security has become of utmost importance. One key element to guarantee an adequate level of security is being able to detect the threat as soon as possible, decreasing the risk of consequences derived from those actions. In this paper, a new metric for early detection system evaluation that takes into account the delay in detection is defined. Time aware F-score (TaF) takes into account the number of items or individual elements processed to determine if an element is an anomaly or if it is not relevant to be detected. These results are validated by means of a dual approach to cybersecurity, Operative System (OS) scan attack as part of systems and network security and the detection of depression in social media networks as part of the protection of users. Also, different approaches, oriented towards studying the impact of single item selection, are applied to final decisions. This study allows to establish that nitems selection method is usually the best option for early detection systems. TaF metric provides, as well, an adequate alternative for time sensitive detection evaluation., This work was supported in part by the Ministry of Economy and Competitiveness of Spain and Fondo Europeo de Desarrollo Regional (FEDER) Funds of the European Union under Project PID2019-111388GB-I00; and in part by the Centro de Investigación de Galicia—Centro de Investigación en Tecnologías de la Información y las Comunicaciones (CITIC) Funded by Xunta de Galicia and the European Union (European Regional Development Fund–Galicia 2014-2020 Program), under Grant ED431G 2019/01., Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

A Content-Based Approach to Profile Expansion

  • Fernández, Diego
  • Formoso, Vreixo
  • Cacheda, Fidel
  • Carneiro, Víctor
[Abstract]: Collaborative Filtering algorithms suffer from the so-called cold-start problem. In particular, when a user has rated few items, recommendations offered by these algorithms are not too accurate. Profile Expansion techniques have been described as a way to tackle this problem without bothering the user with additional information requests by increasing automatically the size of the user profile. Up to now, only collaborative approaches had been proposed for Profile Expansion. However, content-based techniques can also be used. We perform a manual analysis of a movie dataset to analyze how content features behave. According to this analysis, we propose a content-based approach, which is also combined with collaborative information. Concretely, we expose the advantages and disadvantages of the combination with a popularity feature. Moreover, a comparison to pure collaborative approaches is performed. Our approach is evaluated in a new system situation. That is, not only the active user has few ratings, but also most of the users. The results show that content-based information is useful for rating prediction. In addition, recommendations are less personalized as popularity feature acquires more relevance for item selection., This study was supported by the Ministry of Economy and Competitiveness of Spain and FEDER funds of the European Union (Project TIN2015-70648-P), by the Xunta de Galicia (Singular research center of Galicia, accreditation ED431G/01 2016-2019) and the European Union (European Regional Development Fund). This research was supported by the Ministry of Science and Innovation, Spain’s National Research and Development Plan, through the PID2019-111388GB-I00 project., Xunta de Galicia; ED431G/01 2016-2019
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

IoT Dataset Validation Using Machine Learning Techniques for Traffic Anomaly Detection

  • Vigoya, Laura
  • Fernández, Diego
  • Carneiro, Víctor
  • Nóvoa, Francisco
This article belongs to the Special Issue Sensor Network Technologies and Applications with Wireless Sensor Devices, [Abstract] With advancements in engineering and science, the application of smart systems is increasing, generating a faster growth of the IoT network traffic. The limitations due to IoT restricted power and computing devices also raise concerns about security vulnerabilities. Machine learning-based techniques have recently gained credibility in a successful application for the detection of network anomalies, including IoT networks. However, machine learning techniques cannot work without representative data. Given the scarcity of IoT datasets, the DAD emerged as an instrument for knowing the behavior of dedicated IoT-MQTT networks. This paper aims to validate the DAD dataset by applying Logistic Regression, Naive Bayes, Random Forest, AdaBoost, and Support Vector Machine to detect traffic anomalies in IoT. To obtain the best results, techniques for handling unbalanced data, feature selection, and grid search for hyperparameter optimization have been used. The experimental results show that the proposed dataset can achieve a high detection rate in all the experiments, providing the best mean accuracy of 0.99 for the tree-based models, with a low false-positive rate, ensuring effective anomaly detection., This project was funded by the Accreditation, Structuring, and Improvement of Consolidated Research Units and Singular Centers (ED431G/01), funded by Vocational Training of the Xunta de Galicia endowed with EU FEDER funds and Spanish Ministry of Science and Innovation, via the project PID2019-111388GB-I00, Xunta de Galicia; ED431G/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Dataset anotado para detección de anomalías en un CPD con sensores IoT

  • Vigoya, Laura
  • Fernández, Diego
  • Carneiro, Víctor
  • Cacheda, Fidel
Resumo presentado en: XV Jornadas de Ingeniería Telemática (JITEL 2021). 27-29 de outubro de 2021, A Coruña. Traballos dispoñibles en: http://hdl.handle.net/2183/37512, [Resumen] Para detectar anomaías de táfico usando técnicas de aprendizaje automático, es necesario obtener un conocimiento básico del rendimiento y comportamiento de la red. Por ello este trabajo presenta DAD, un conjunto de datos contextualizado, etiquetado y con un análisis sistemático, que reproduce el comportamiento de una red real. DAD presenta siete días de actividad con tres tipos de anomalías: duplicación, interceptación y modificación. Sobre el conjunto de datos se aplica ingeniería de características, para que así puedan ser aplicadas técnicas de clasificación usando algoritmos de aprendizaje automático., Este trabajo fue parcialmente financiado por el Ministerio de Ciencia e Innovación, Plan Nacional de Investigación y Desarrollo (proyecto PID2019-111388GB-I00)., http://hdl.handle.net/2183/37512
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Real-Time Network Auditing System Based on Low-Cost IoT Devices

  • Fernández-Arruti Gallego, Pedro
  • Mosteiro Vázquez, Alejandro
  • Dafonte, Carlos
  • Fernández, Diego
  • Novoa-Blanco, Francisco J.
Presentado en: International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2022), 29 Nov.-2 Dic, Córdoba (España) This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-031-21333-5_106, [Abstract] Nowadays, the commercial activity of all types of companies depends significantly on their networks and the security of their IT systems. Despite this, there are studies that show deficiencies in cybersecurity, particularly in small and medium-sized enterprises (SMEs). This is due to the fact that only generic, costly and difficult to interpret security solutions are available in the current literature. As we can see, it is necessary to create a security audit system, aimed at SMEs and, therefore, low cost, easy to use and interpret and that can be adapted to networks of different types and sizes. For this reason, we have created a network audit system based on low-cost hardware boards. This consists of a series of sensors that analyze the networks and a central server that allows us to give persistence to the information through a data streaming system and, in addition, create a web application in which to view the information of all the audited companies. As a result, we have obtained a tool capable of creating an inventory of all the organisation’s network assets, through active and passive analysis; capable of listing the vulnerabilities of the assets, indicating their level of severity and, in addition, capable of performing WiFi analysis. On the other hand, we want to highlight some important non-functional features to meet the main objective: it is a low-cost, scalable and modular solution that adapts to any format and size of network and, in addition, it is easy to use and understand, aimed to non-expert personnel., This work made use of the infrastructures acquired with Grants provided by the State Research Agency (AEI) of the Spanish Government and the European Regional Development Fund (FEDER), through RTI2018-095076-B-C22, PID2019-111388GB-I00 and PID2021-122842OB-C22. We acknowledge support from CIGUS-CITIC, funded by Xunta de Galicia and the European Union (FEDER Galicia 2014–2020 Program) through Grant ED431G 2019/01; research consolidation Grant ED431B 2021/36; and scholarship from Xunta de Galicia and the European Union (European Social Fund - ESF) ED481A-2019/155., Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED431B 2021/36, Xunta de Galicia; ED481A-2019/155
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Interception of BLE Communications in Wearables: An Application Case

  • Seco Fontecoba, Adrián
  • Fernández-Arruti Gallego, Pedro
  • Dafonte, Carlos
  • Novoa-Blanco, Francisco J.
Presentado en: International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2022), 29 Nov.-2 Dic, Córdoba (España) This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-031-21333-5_102, [Abstract] The number of people who care about their health and physical condition and who begin to practice different sports or activities related to the fitness field is increasing. This is the reason why, in recent years, the use of activity bracelets or smartbands has become popular. These are devices that allow us to monitor some parameters of our body such as heart rate, blood oxygen saturation or the quality of our sleep, among other things. Sometimes, the manufacturers and developers of this type of device are primarily concerned with improving the characteristics of communication and data transmission between the bracelets and the smartphones in which we can see the data collected, leaving aside the security of the same. This is a serious problem due to the fact that the information we are working with is very sensitive information about the user, related to their basic medical data. In this paper, we intend to carry out an in-depth study related to the operation of this type of devices, analyzing its level of security. With this, we have verified that the main point of failure of wearable devices is in the communication between them and the smartphones that control them. It is possible to carry out Man-in-the-Middle attacks, which allow us to intercept all the traffic sent between both devices in real time. In this document we show how to execute this attack and be able to listen to all the traffic transmitted between an smartband and the smartphone that manages it., This work made use of the infrastructures acquired with Grants provided by the State Research Agency (AEI) of the Spanish Government and the European Regional Development Fund (FEDER), through RTI2018–095076–B–C22, PID2019–111388GB–I00 and PID2021–122842OB–C22. We acknowledge support from CIGUS–CITIC, funded by Xunta de Galicia and the European Union (FEDER Galicia 2014–2020 Program) through Grant ED431G 2019/01; research consolidation Grant ED431B 2021/36; and scholarship from Xunta de Galicia and the European Union (European Social Fund – ESF) ED481A–2019/155., Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED431B 2021/36, Xunta de Galicia; ED481A–2019/155
RUC. Repositorio da Universidade da Coruña
Publicación

Auditoría Wi-Fi basada en placas de bajo coste

  • Otero Dans, Anxo
  • Dafonte, Carlos
  • Fernández, Diego
  • Cacheda, Fidel
  • López-Vizcaíno, Manuel F.
  • Nóvoa, Francisco
En Libro de Actas de XV Jornadas de Ingeniería Telemática (JITEL), A Coruña 2021., [Resumen]: En la actualidad, el uso de redes inalámbricas crece exponencialmente en entornos empresariales de todo tipo. Si bien es cierto que existen una gran cantidad de soluciones en el ámbito de auditoría de redes inalámbricas para grandes organizaciones, las soluciones que existen para las pequeñas empresas son escasas, y esto junto a la falta de conocimientos y experiencia en Tecnologías de la Información (TI) del personal de dichas organizaciones, provoca que este tipo de empresas se encuentren habitualmente en un nivel de riesgo en ciberseguridad alto. En este contexto desarrollamos una herramienta que tiene como objetivo la auditoría de redes inalámbricas en entornos empresariales, basada en hardware de bajo coste y que requiera, únicamente, un nivel básico de conocimientos de TI y ciberseguridad por parte del usuario. El diseño arquitectónico de la herramienta se basa en un sistema distribuido de dispositivos de bajo coste que permite monitorizar y auditar el entorno inalámbrico y mostrar la información obtenida al usuario de forma inteligible. En la implementación actual utilizamos Raspberry Pi 3B+ como placas de bajo coste, a las que conectamos antenas Wi-Fi externas, que facilitan la captura de tráfico de red. Posteriormente, procesamos dicho tráfico y los resultados obtenidos se muestran al usuario mediante una interfaz web. Tras la finalización del desarrollo de la herramienta, hemos realizado pruebas, tanto en un entorno real como en un entorno simulado, lo que nos ha permitido obtener interesantes conclusiones acerca del trabajo realizado., Esta investigación ha sido financiada por el Ministerio de Economía y Competitividad de España y fondos FEDER de la UE (Proyecto PID2019-525 111388GB-I00) y por el Centro de Investigación de Galicia "CITIC", financiado por la Xunta de Galicia y la UE (Fondo de Desarrollo Regional Europeo - Programa Galicia 2014- 2020), mediante la concesión de ED431G 2019/01, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Application of machine learning algorithms for the validation of a new CoAP-IoT anomaly detection dataset

  • Vigoya, Laura
  • Pardal Noya, Alberto
  • Fernández, Diego
  • Carneiro, Víctor
[Abstract]: With the rise in smart devices, the Internet of Things (IoT) has been established as one of the preferred emerging platforms to fulfil their need for simple interconnections. The use of specific protocols such as constrained application protocol (CoAP) has demonstrated improvements in the performance of the networks. However, power-, bandwidth-, and memory-constrained sensing devices constitute a weakness in the security of the system. One way to mitigate these security problems is through anomaly-based intrusion detection systems, which aim to estimate the behaviour of the systems based on their “normal” nature. Thus, to develop anomaly-based intrusion detection systems, it is necessary to have a suitable dataset that allows for their analysis. Due to the lack of a public dataset in the CoAP-IoT environment, this work aims to present a complete and labelled CoAP-IoT anomaly detection dataset (CIDAD) based on real-world traffic, with a sufficient trace size and diverse anomalous scenarios. The modelled data were implemented in a virtual sensor environment, including three types of anomalies in the CoAP data. The validation of the dataset was carried out using five shallow machine learning techniques: logistic regression, naive Bayes, random forest, AdaBoost, and support vector machine. Detailed analyses of the dataset, data conditioning, feature engineering, and hyperparameter tuning are presented. The evaluation metrics used in the performance comparison are accuracy, precision, recall, F1 score, and kappa score. The system achieved 99.9% accuracy for decision tree models. Random forest established itself as the best model, obtaining a 99.9% precision and F1 score, 100% recall, and a Cohen’s kappa statistic of 0.99., This project was funded by the Accreditation, Structuring, and Improvement of Consolidated Research Units and Singular Centers (ED431G/01), funded by Vocational Training of the Xunta de Galicia endowed with EU FEDER funds and Spanish Ministry of Science and Innovation, via the project PID2019-111388GB-I00.
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Early Detection of Cyberbullying on Social Media Networks

  • López-Vizcaíno, Manuel F.
  • Nóvoa, Francisco
  • Carneiro, Víctor
  • Cacheda, Fidel
[Abstract] Cyberbullying is an important issue for our society and has a major negative effect on the victims, that can be highly damaging due to the frequency and high propagation provided by Information Technologies. Therefore, the early detection of cyberbullying in social networks becomes crucial to mitigate the impact on the victims. In this article, we aim to explore different approaches that take into account the time in the detection of cyberbullying in social networks. We follow a supervised learning method with two different specific early detection models, named threshold and dual. The former follows a more simple approach, while the latter requires two machine learning models. To the best of our knowledge, this is the first attempt to investigate the early detection of cyberbullying. We propose two groups of features and two early detection methods, specifically designed for this problem. We conduct an extensive evaluation using a real world dataset, following a time-aware evaluation that penalizes late detections. Our results show how we can improve baseline detection models up to 42%., This research was supported by the Ministry of Economy and Competitiveness of Spain and FEDER funds of the European Union (Project PID2019-111388GB-I00) and by the Centro de Investigación de Galicia “CITIC”, funded by Xunta de Galicia (Galicia, Spain) and the European Union (European Regional Development Fund — Galicia 2014–2020 Program) , by grant ED431G 2019/01, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Use of Machine Learning Algorithms for Network Traffic Classification

  • Nieto Antelo, Adrián
  • Fernández, Diego
  • Nóvoa, Francisco
Cursos e Congresos , C-155, [Abstract] In recent years, the complexity of threats utilizing the network as an attack vector has significantly increased. Traditional attack prevention and detection systems (IPS/IDS) based on signatures do not provide an acceptable level of security for many organizations. Furthermore, the volume of traffic on corporate networks has also grown exponentially, while quality of service requirements do not always allowfor deep inspection (at the application layer) of packets. The main objective of this work is to demonstrate that the application of machine learning techniques to the information of data flows circulating through the network allows for the satisfactory detection of malicious traffic. Specifically, this work is developed within an emerging network paradigm, such as software-defined networks., This research has been funded by the Spanish Ministry of Economy and Competitiveness and European Union ERDF funds (Project PID2019-111388GB-I00). CITIC is funded by the Xunta de Galicia through the collaboration agreement between the Conseller´ıa de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS)
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Detección temprana de cyberbullying en redes sociales

  • López-Vizcaíno, Manuel F.
  • Nóvoa, Francisco
  • Carneiro, Víctor
  • Cacheda, Fidel
Resumo presentado en: XV Jornadas de Ingeniería Telemática (JITEL 2021). 27-29 de outubro de 2021, A Coruña, [Resumen] En este resumen presentamos dos enfoques que tienen en cuenta el tiempo en la detección del cyberbullying en redes sociales. Siguiendo un método de aprendizaje máquina supervisado, definimos dos modelos específicos de detección temprana, denominados umbral y dual. El primero sigue un enfoque más simple, mientras que el segundo requiere dos modelos de aprendizaje automático. Como contribuciones principales destacar la definición de dos grupos de características y dos métodos de detección temprana, diseñados específicamente para este problema. Realizamos una evaluación pormenorizada utilizando un conjunto de datos real y siguiendo una evaluación basada en el tiempo que penaliza las detecciones tardías. Nuestros resultados demuestran que somos capaces de mejorar los modelos de detección de referencia hasta un 42%., Esta investigación ha sido financiada por el Ministerio de Economía y Competitivad de España y fondos FEDER de la Unión Europea (Proyecto PID2019-111388GB-I00) y por el Centro de Investigación de Galicia "CITIC", financiado por la Xunta de Galicia y la Unión Europea (programa FEDER GALICIA 2014-2020), mediante la ayuda ED431G 2019/01., Xunta de Galicia; ED431G 2019/01, https://www.scitel.es/jitel/actas/Actas_Jitel_2021_A_Coru%C3%B1a.pdf