Publication

Abstract : The extensive growth of internet users provides the opportunities for anomalies to intrude our privacy and security. Phishing is one among them that has turned out to be a major issue in the recent times, that directly hit specific targeted group of people asking for their credentials, personal and other sensitive information. This paper elaborates the module submitted to IWSPA-AP Shared Task at IWSPA 2018 that focuses on distinguishing the phishing and legitimate emails. In fundamental it is a text classification problem in which representation serves as the core component and also has a direct relationship to the final performance. This work assess and reports the performance of distributed representation in detection of phishing emails as a text classification problem. The word embedding and neural bag-of-ngrams facilitates to extract syntactic and semantic similarity of emails. The experimented module obtains promising and consistence performance on both the train and test corpus in-terms of time and accuracy. The model obtains 99% and 97% as the f1 score on the unseen test corpus. Copyright © by the paper's authors.