Skip to main content

INTEGRACION DE CONOCIMIENTO SEMANTICO PARA EL FILTRADO DE SPAM BASADO EN CONTENIDO

TIN2017-84658-C2-1-R

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos I+D+i Retos de Investigación
Call year 2017
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSIDAD DE VIGO

Resultados relacionados

Resultados totales (Incluyendo duplicados): 10
Encontrada(s) 1 página(s)

Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

Deobfuscating Leetspeak with deep learning to improve spam filtering

  • Vélez de Mendizabal, Iñaki
  • Vidriales, Xabier
  • Basto Fernandes, Vitor
  • Ezpeleta, Enaitz
  • Méndez Reboredo, José Ramón
  • Zurutuza, Urko
The evolution of anti-spam filters has forced spammers to make greater efforts to bypass filters in order to distribute content over networks. The distribution of content encoded in images or the use of Leetspeak are concrete and clear examples of techniques currently used to bypass filters. Despite the importance of dealing with these problems, the number of studies to solve them is quite small, and the reported performance is very limited. This study reviews the work done so far (very rudimentary) for Leetspeak deobfuscation and proposes a new technique based on using neural networks for decoding purposes. In addition, we distribute an image database specifically created for training Leetspeak decoding models. We have also created and made available four different corpora to analyse the performance of Leetspeak decoding schemes. Using these corpora, we have experimentally evaluated our neural network approach for decoding Leetspeak. The results obtained have shown the usefulness of the proposed model for addressing the deobfuscation of Leetspeak character sequences., Agencia Estatal de Investigación | Ref. TIN2017-84658-C2-1-R, Agencia Estatal de Investigación | Ref. TIN2017-84658-C2-2-R, Fundação para a Ciência e a Tecnologia | Ref. UIDB/04466/2020, Fundação para a Ciência e a Tecnologia | Ref. UIDP/04466/2020
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

Multi-objective evolutionary optimization for dimensionality reduction of texts represented by synsets

  • Vélez de Mendizabal, Iñaki
  • Basto Fernandes, Vitor
  • Ezpeleta, Enaitz
  • Méndez Reboredo, José Ramón
  • Gómez Meire, Silvana
  • Zurutuza, Urko
Despite new developments in machine learning classification techniques, improving the accuracy of spam filtering is a difficult task due to linguistic phenomena that limit its effectiveness. In particular, we highlight polysemy, synonymy, the usage of hypernyms/hyponyms, and the presence of irrelevant/confusing words. These problems should be solved at the pre-processing stage to avoid using inconsistent information in the building of classification models. Previous studies have suggested that the use of synset-based representation strategies could be successfully used to solve synonymy and polysemy problems. Complementarily, it is possible to take advantage of hyponymy/hypernymy-based to implement dimensionality reduction strategies. These strategies could unify textual terms to model the intentions of the document without losing any information ( e.g. , bringing together the synsets “viagra”, “ciallis”, “levitra” and other representing similar drugs by using “virility drug” which is a hyponym for all of them). These feature reduction schemes are known as lossless strategies as the information is not removed but only generalised. However, in some types of text classification problems (such as spam filtering) it may not be worthwhile to keep all the information and let dimensionality reduction algorithms discard information that may be irrelevant or confusing. In this work, we are introducing the feature reduction as a multi-objective optimisation problem to be solved using a Multi-Objective Evolutionary Algorithm (MOEA). Our algorithm allows, with minor modifications, to implement lossless (using only semantic-based synset grouping), low-loss (discarding irrelevant information and using semantic-based synset grouping) or lossy (discarding only irrelevant information) strategies. The contribution of this study is two-fold: (i) to introduce different dimensionality reduction methods (lossless, low-loss and lossy) as an optimization problem that can be solved using MOEA and (ii) to provide an experimental comparison of lossless and low-loss schemes for text representation. The results obtained support the usefulness of the low-loss method to improve the efficiency of classifiers., Agencia Estatal de Investigación | Ref. TIN2017-84658-C2-1-R, Agencia Estatal de Investigación | Ref. TIN2017-84658-C2-2-R, Xunta de Galicia | Ref. ED431C 2022/03-GRC, Eusko Jaurlaritza | Ref. IT1676-22, Fundação para a Ciência e a Tecnologia | Ref. UIDB/04466/2020, Fundação para a Ciência e a Tecnologia | Ref. UIDP/04466/2020
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

A practical approach to protect IoT devices against attacks and compile security incident datasets

  • Cruz, Bruno
  • Gómez Meire, Silvana
  • Ruano Ordás, David Alfonso
  • Janicke, Helge
  • Yevseyeva, Iryna
  • Méndez Reboredo, José Ramón
The Internet of Things (IoT) introduced the opportunity of remotely manipulating home appliances (such as heating systems, ovens, blinds, etc.) using computers and mobile devices. This idea fascinated people and originated a boom of IoT devices together with an increasing demand that was difficult to support. Many manufacturers quickly created hundreds of devices implementing functionalities but neglected some critical issues pertaining to device security. This oversight gave rise to the current situation where thousands of devices remain unpatched having many security issues that manufacturers cannot address after the devices have been produced and deployed. This article presents our novel research protecting IOT devices using Berkeley Packet Filters (BPFs) and evaluates our findings with the aid of our Filter.tlk tool, which is able to facilitate the development of BPF expressions that can be executed by GNU/Linux systems with a low impact on network packet throughput., Xunta de Galicia | Ref. ED481B 2017/018, Ministerio de Economía y Competitividad | Ref. TIN2017-84658-C2-1-R, Xunta de Galicia | Ref. ED431C2018/55-GRC
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

Using natural language preprocessing architecture (NLPA) for Big Data text sources

  • Novo Lourés, María
  • Pavón Rial, Maria Reyes
  • Laza Fidalgo, Rosalía
  • Ruano Ordás, David Alfonso
  • Méndez Reboredo, José Ramón
During the last years, big data analysis has become a popular means of taking advantage of multiple (initially valueless) sources to find relevant knowledge about real domains. However, a large number of big data sources provide textual unstructured data. A proper analysis requires tools able to adequately combine big data and text-analysing techniques. Keeping this in mind, we combined a pipelining framework (BDP4J (Big Data Pipelining For Java)) with the implementation of a set of text preprocessing techniques in order to create NLPA (Natural Language Preprocessing Architecture), an extendable open-source plugin implementing preprocessing steps that can be easily combined to create a pipeline. Additionally, NLPA incorporates the possibility of generating datasets using either a classical token-based representation of data or newer synset-based datasets that would be further processed using semantic information (i.e., using ontologies). This work presents a case study of NLPA operation covering the transformation of raw heterogeneous big data into different dataset representations (synsets and tokens) and using the Weka application programming interface (API) to launch two well-known classifiers., Xunta de Galicia | Ref. ED481B 2017/018, Agencia Estatal de Investigación | Ref. TIN2017-84658-C2-1-R
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

Enhancing representation in the context of multiple-channel spam filtering

  • Novo Lourés, María
  • Ruano Ordás, David Alfonso
  • Pavón Rial, Maria Reyes
  • Laza Fidalgo, Rosalía
  • Gómez Meire, Silvana
  • Méndez Reboredo, José Ramón
Financiado para publicación en acceso aberto: Universidade de Vigo/CISUG, This study addresses the usage of different features to complement synset-based and bag-of-words representations of texts in the context of using classical ML approaches for spam filtering (Ferrara, 2019). Despite the existence of a large number of complementary features, in order to improve the applicability of this study, we have selected only those that can be computed regardless of the communication channel used to distribute content. Feature evaluation has been performed using content distributed through different channels (social networks and email) and classifiers (Adaboost, Flexible Bayes, Naïve Bayes, Random Forests, and SVMs). The results have revealed the usefulness of detecting some non-textual entities (such as URLs, Uniform Resource Locators) in the addressed distribution channels. Moreover, we also found that compression properties and/or information regarding the probability of correctly guessing the language of target texts could be successfully used to improve the classification in a wide range of situations. Finally, we have also detected features that are influenced by specific fashions and habits of users of certain Internet services (e.g. the existence of words written in capital letters) that are not useful for spam filtering., Xunta de Galicia | Ref. ED481D-2021/024, Agencia Estatal de Investigación | Ref. TIN2017-84658-C2-1-R
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

An enhanced algorithm for semantic-based feature reduction in spam filtering

  • Novo Lourés, María
  • Pavón Rial, Maria Reyes
  • Laza Fidalgo, Rosalía
  • Méndez Reboredo, José Ramón
  • Ruano Ordás, David Alfonso
With the advent and improvement of ontological dictionaries (WordNet, Babelnet), the use of synsets-based text representations is gaining popularity in classification tasks. More recently, ontological dictionaries were used for reducing dimensionality in this kind of representation ( e.g. , Semantic Dimensionality Reduction System (SDRS) (Vélez de Mendizabal et al., 2020)). These approaches are based on the combination of semantically related columns by taking advantage of semantic information extracted from ontological dictionaries. Their main advantage is that they not only eliminate features but can also combine them, minimizing (low-loss) or avoiding (lossless) the loss of information. The most recent (and accurate) techniques included in this group are based on using evolutionary algorithms to find how many features can be grouped to reduce false positive (FP) and false negative (FN) errors obtained. The main limitation of these evolutionary-based schemes is the computational requirements derived from the use of optimization algorithms. The contribution of this study is a new lossless feature reduction scheme exploiting information from ontological dictionaries, which achieves slightly better accuracy (specially in FP errors) than optimization-based approaches but using far fewer computational resources. Instead of using computationally expensive evolutionary algorithms, our proposal determines whether two columns (synsets) can be combined by observing whether the instances included in a dataset ( e.g. , training dataset) containing these synsets are mostly of the same class. The study includes experiments using three datasets and a detailed comparison with two previous optimization-based approaches., Xunta de Galicia | Ref. ED431C 2022/03-GRC, Agencia Estatal de Investigación | Ref. Ref. TIN2017-84658-C2-1-R
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

Improvements for research data repositories: The case of text spam

  • Vázquez, Ismael
  • Novo Lourés, María
  • Pavón Rial, Maria Reyes
  • Laza Fidalgo, Rosalía
  • Méndez Reboredo, José Ramón
  • Ruano Ordás, David Alfonso
Current research has evolved in such a way scientists must not only adequately describe the algorithms they introduce and the results of their application, but also ensure the possibility of reproducing the results and comparing them with those obtained through other approximations. In this context, public data sets (sometimes shared through repositories) are one of the most important elements for the development of experimental protocols and test benches. This study has analysed a significant number of CS/ML (Computer Science/ Machine Learning) research data repositories and data sets and detected some limitations that hamper their utility. Particularly, we identify and discuss the following demanding functionalities for repositories: (1) building customised data sets for specific research tasks, (2) facilitating the comparison of different techniques using dissimilar pre-processing methods, (3) ensuring the availability of software applications to reproduce the pre-processing steps without using the repository functionalities and (4) providing protection mechanisms for licencing issues and user rights. To show the introduced functionality, we created STRep (Spam Text Repository) web application which implements our recommendations adapted to the field of spam text repositories. In addition, we launched an instance of STRep in the URL https://rdata.4spam.group to facilitate understanding of this study, Xunta de Galicia | Ref. ED431C 2021/44, Agencia Estatal de Investigación | Ref. TIN2017-84658-C2-1-R
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

A new semantic-based feature selection method for spam filtering

  • Méndez Reboredo, José Ramón
  • Cotos Yáñez, Tomas Raimundo
  • Ruano Ordás, David Alfonso
The Internet emerged as a powerful infrastructure for the worldwide communication and interaction of people. Some unethical uses of this technology (for instance spam or viruses) generated challenges in the development of mechanisms to guarantee an affordable and secure experience concerning its usage. This study deals with the massive delivery of unwanted content or advertising campaigns without the accordance of target users (also known as spam). Currently, words (tokens) are selected by using feature selection schemes; they are then used to create feature vectors for training different Machine Learning (ML) approaches. This study introduces a new feature selection method able to take advantage of a semantic ontology to group words into topics and use them to build feature vectors. To this end, we have compared the performance of nine well-known ML approaches in conjunction with (i) Information Gain, the most popular feature selection method in the spam-filtering domain and (ii) Latent Dirichlet Allocation, a generative statistical model that allows sets of observations to be explained by unobserved groups that describe why some parts of the data are similar, and (iii) our semantic-based feature selection proposal. Results have shown the suitability and additional benefits of topic-driven methods to develop and deploy high-performance spam filters., Xunta de Galicia | Ref. ED481B 2017/018, Xunta de Galicia | Ref. ED431C 2016-040, Agencia Estatal de Investigación | Ref. MTM2017-89422-P, Agencia Estatal de Investigación | Ref. TIN2017-84658-C2-1-R
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

Improving pipelining tools for pre-processing data

  • Novo Lourés, María
  • Lage, Yeray
  • Pavón Rial, Maria Reyes
  • Laza Fidalgo, Rosalía
  • Ruano Ordás, David Alfonso
  • Méndez Reboredo, José Ramón
The last several years have seen the emergence of data mining and its transformation into a powerful tool that adds value to business and research. Data mining makes it possible to explore and find unseen connections between variables and facts observed in different domains, helping us to better understand reality. The programming methods and frameworks used to analyse data have evolved over time. Currently, the use of pipelining schemes is the most reliable way of analysing data and due to this, several important companies are currently offering this kind of services. Moreover, several frameworks compatible with different programming languages are available for the development of computational pipelines and many research studies have addressed the optimization of data processing speed. However, as this study shows, the presence of early error detection techniques and developer support mechanisms is very limited in these frameworks. In this context, this study introduces different improvements, such as the design of different types of constraints for the early detection of errors, the creation of functions to facilitate debugging of concrete tasks included in a pipeline, the invalidation of erroneous instances and/or the introduction of the burst-processing scheme. Adding these functionalities, we developed Big Data Pipelining for Java (BDP4J, https://github.com/sing-group/bdp4j), a fully functional new pipelining framework that shows the potential of these features., Agencia Estatal de Investigación | Ref. TIN2017-84658-C2-1-R, Xunta de Galicia | Ref. ED481D-2021/024, Xunta de Galicia | Ref. ED431C2018/55-GRC
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

An ontology knowledge inspection methodology for quality assessment and continuous improvement

  • Roldán Molina, Gabriela R.
  • Ruano Ordás, David Alfonso
  • Basto Fernandes, Vitor
  • Méndez Reboredo, José Ramón
Financiado para publicación en acceso aberto: Universidade de Vigo/CISUG, Ontology-learning methods were introduced in the knowledge engineering area to automatically build ontologies from natural language texts related to a domain. Despite the initial appeal of these methods, automatically generated ontologies may have errors, inconsistencies, and a poor design quality, all of which must be manually fixed, in order to maintain the validity and usefulness of automated output. In this work, we propose a methodology to assess ontologies quality (quantitatively and graphically) and to fix ontology inconsistencies minimizing design defects. The proposed methodology is based on the Deming cycle and is grounded on quality standards that proved effective in the software engineering domain and present high potential to be extended to knowledge engineering quality management. This paper demonstrates that software engineering quality assessment approaches and techniques can be successfully extended and applied to the ontology-fixing and quality improvement problem. The proposed methodology was validated in a testing ontology, by ontology design quality comparison between a manually created and automatically generated ontology., Xunta de Galicia | Ref. ED481B 2017/018, Xunta de Galicia | Ref. ED431C2018 / 55-GRC, Ministerio de Economía, Industria y Competitividad | Ref. TIN2017-84658-C2-1-R