Abstract:

Due to its ongoing use of servers' and receivers' resources, email spam is becoming more and more popular. In this paper, we introduce ESHIELD, a unique email spam filtering protocol that employs big data analytics to protect against spam emails. In order to lighten the load on the server, the protocol is carried out at the receiver end for precise and quick filtering. ESHIELD's primary objective is to identify spammers and anyone else who sends spam emails. Using parameters like false positive rate, false negative rate, detection accuracy, and detection time, the performance of the ESHIELD implementation, which makes use of the Map Reduce feature of the Hadoop framework, has been assessed. By building probabilistic models on the suspected email, ESHIELD speeds up the spam detection process. Additionally, it applies similarity tests to the emails to reliably identify spam with a minimal amount of false positives and negatives.

Description:

Feature, Cluster, Map reduce, Features, Spam Email, Similarity, Probabilistic