RT Dissertation/Thesis
T1 Model for optimising the execution of anti-spam filters
A1 Ruano Ordas, David Alfonso
K1 1203.04 Inteligencia Artificial
K1 1203.11 Logicales de Ordenadores
K1 1203.17 Informática
AB The establishment of the first interconnection between two remote hosts in 1969 originated the beginning of one of the most important technological phenomena of humanity, Internet. In fact, Internet has become an essential part of life for many people inhabiting the most industrialized nations, reaching a percentage of penetration during 2014 of 40% of the world population. One of the reasons that propitiated the massive proliferation of Internet is attributable to the e-mail. This service allows an easy and fast (nearly instantaneous) communication between users by sending messages. This fact has meant that e-mail service acquired a surprising popularity. However, the uncontrolled nature of Internet has turned e-mail communications into the best framework for the promotion of illegal advertisements (such as those about drugs selling), the delivery of phishing e-mails, the virus propagation and other forms of electronic scam (also called spam). Although the amount of spam e-mail deliveries undergoes continuous fluctuations, current statistics show that more than 60% of the e-mail transferred through Internet are spam. This spam ratio is supported by newest communication advances such as 4G new generation networks, ensures a quick an easy Internet connection almost everywhere.Under these circunstances, the use of spam filtering services and products is the most effective mechanism to fight against spam. However, the massive amount of e-mail deliveries per day (an average of 125 billion in 2015) has encouraged the need of improving spam filtering services in order to adapt them to the current needs.In this research work, is introduce a new filtering model able to enhance speed and accuracy while maintaining the same philosophy and anti-spam techniques used in the most popular anti-spam filtering systems. This goal has been achieved through improving several aspects including: (i) the design and development of small technical improvements to enhance overall filter throughput, (ii) the application of genetic algorithms in order to enhance the filter accuracy and finally, (iii) the use of scheduling algorithms to increase speed filtering.
YR 2015
FD 2015-07-24
LK http://hdl.handle.net/11093/371
UL http://hdl.handle.net/11093/371
LA eng
NO Xunta de Galicia | Ref. 08TIC041E
DS Investigo
RD 10-dic-2023