SpamBands: uma metodologia para identificação de fontes de spam agindo de forma orquestrada

Elverton FazzionPedro Henrique B. Las-CasasOsvaldo FonsecaDorgival GuedesWagner Meira Jr.Cristine HoepersKlaus Steding-JessenMarcelo H. P. Chaves

In 2012, estimates indicated that 68.8% of all e-mail traffic was spam, what suggests this is still a relevant problem. Recently, some works have focused on the analysis of spam's traffic inside the network, analyzing the protocols used and the AS which originate the traffic. However, those works usually do not consider the relationships between the machines used to send spam. Such an analysis could reveal how different machines may be used by a single spammer to spread his messages, helping us to understand their behavior. To that end, this work proposes a methodology to cluster the machines used by spammers based on the concept of spam campaigns. The groups identified were characterized to identify different aspects of the spam dissemination process, which suggest different orchestration strategies being used.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: