Spam E-mail Filtering using ECOS Algorithms

Abstract

Spam known as Unsolicited Bulk E-mail (UBE) including undesirable electronic correspondence that is sent in bulk to massive mailing lists, sometimes with some business nature sent get into bulk. One of the main problems of spam E-mail detection is an attack from an unknown source known as ‘zero-day’ so named due to continued changes in timing. Zero day attacks are problematic for having the ability to escape spamming detection as the hosts do not show up in blacklists. This adds to the problem of False positives and OCR computational cost especially in dealing with a huge corpus of texts with images that run through server-side filters. Spammers are busy orchestrating various representation techniques thus making their ‘zero-day’ spam E-mail that infiltrate the defenses of detection. Our proposed is a novel system called Spamming Dynamic Evolving Neural Fuzzy System (SDENFS), which adapts the Evolving Connectionist System (ECoS) based on a hybrid (supervised/unsupervised) learning approach. SDENFS adaptive online is enhanced by offline learning to detect dynamically the spamming E-mail included unknown zero-day spamming E-mails before it get to user account. SDENFS is suggested to work for high-speed “life-long” learning with low memory footprint with few number of rules creation for E-mail classification. Two datasets composed of 6612 samples of spam and legitimate E-mails were used to assess the proposed system. The proposed system showed a high level of performance in detecting spam E-mail attacks. The average of the accuracy and F-measure of the classification process was 99%.