Informática
URI permanente para esta comunidadhttps://hdl.handle.net/11441/33181
Examinar
Examinando Informática por Autor "Aláiz Rodríguez, Rocío"
Mostrando 1 - 2 de 2
- Resultados por página
- Opciones de ordenación
Ponencia A review of Spotting Child Sexual Exploitation Material using File Names and their Path [Póster](Universidad de Sevilla. Escuela Técnica Superior de Ingeniería Informática, 2024) Al-Nabki, MHD Wesam; Jáñez Martino, Francisco; Fidalgo, Eduardo; Alegre, Enrique; Aláiz Rodríguez, RocíoLaw Enforcement Agencies (LEAs) fight the pro duction and distribution of Child Sexual Exploitation Material (CSEM) daily. Typically, the LEAs engage in manual analysis of the content stored on seized devices suspected of containing CSEM data. This task is complex and time-consuming because of the number of files and the obfuscation and patterns that sexual offenders might use in the file names. We proposed two Natural Language Processing approaches: f irst, training two text classifiers—one dedicated to analyzing f ilenames and the other to examining absolute paths—and then merging their output into a single output. The second uses only the filename classifier recursively over the absolute path. Moreover, we incorporated in both approaches three novel features to enrich the character n-gram representation before training four machine learning classifiers and two Convolutional Neural Networks (CNN). For CSEM detection, we recommend a CNN model combining both approaches, with an F1-score of 0,988, which was integrated into the tool built in the European Project: Global Response Against Child Exploitation (GRACE).Ponencia Familiarity Analysis and Phishing Website Detection using PhiKitA Dataset [Póster](Universidad de Sevilla. Escuela Técnica Superior de Ingeniería Informática, 2024) Castaño, Felipe; Martínez Mendoza, Alicia; Fidalgo, Eduardo; Aláiz Rodríguez, Rocío; Alegre, EnriquePhishing kits are tools used by phishers to deploy phishing attacks faster, more easily and on a larger scale. Detecting phishing kits could aid in the early detection of phishing campaigns by recognizing patterns resulting from the use of phishing kits in the creation of the attack. In this paper, we proposed a methodology to collect phishing kit data and created PhiKitA, a novel dataset that contains phishing kits and websites generated with them. Using PhiKitA, we performed three ex periments (familiarity analysis, phishing website detection, and multiclass classification of phishing kits) and evaluated three algorithms: MD5 hashes, fingerprints, and graph representation DOM. The first experiment shows evidence of different phishing kits, the second indicates that the algorithms retrieve useful information to detect phishing with an accuracy of 92.50%, and the third experiment indicates that the algorithms do not retrieve enough information to classify phishing.