Improved Spam Detection using DBSCAN and Advanced Digest Algorithm

Abstract

E-mail is one of the most popular and frequently used ways of communication due to its worldwide accessibility, relatively fast message transfer, and low sending cost. Nowadays, detecting and filtering are still the most feasible ways of fighting spam emails. There are many reasonably successful spam email filters in operation. The identification of spam plays an important role in current anti-spam mechanism.For improving the accuracy of spam detection, an improved Filtering technique is presented which is based on the Improved Digest algorithm and DBSCAN clustering algorithm.Using this technique, mails are represented using improved digest algorithm and then clustered using DBSCAN clustering algorithm. All similar emails which always categorized as spam are identified and clustered together where good mails that don't look similar like other mails are not clustered. This method greatly improves the filtering accuracy against latest proposed algorithms by 30 % and improves the resistance of spam detection against increased obfuscation effort by spammers, while keeping miss-detection of good emails at a similar level of older filtering methods.

Machine Learning Techniques for Spam Detection in Email and IoT Platforms: Analysis and Research Challenges

“…Hierarchical clustering and partitioning clustering are commonly used clustering techniques. Ahmed [80] used DBSCAN clustering and an improved digest algorithm to classify emails. He used the spam assassin dataset for the development of his model.…”

“…Among all the researchers, Sharma Rastogi [78] and Ahmed et al got the highest accuracy level using DBSCAN and K-mean algorithm, respectively, for the email spam detection. Ahmed [80] used spam assassin dataset for the implementation of his model.…”

“…Ahmed [80] used an improved digest algorithm with DBSCAN clustering to classify spam emails. ey create a different digest (parts) of emails before clustering.…”

Unsupervised Approach for Email Spam Filtering using Data Mining

“…Figure (2) illustrates the output clusters using one of the cluster analysis methods, and it is three groups (A, B and C) in coordinate space. Furthermore, some cluster analysis is applied to produce clusters with different size and densities [11]. In this study, the M-DBSCAN has been proposed to classify the spam, and hame emails using the Kaggle dataset, which consists of spam and ham emails with (4993) uniques values spam emails 29% and the ham emails with 71%.…”

Spam Detection using Reference Text: A Preliminary Study for Spam Ground Truth Generation

“…Not only machine learning but deep learning techniques are also used extensively to generate efficient models with high metric values. In Kaddouraet al [9] we have a method that is comparing the results of two state-of-the-art models FFNN(Feed Forward Neural Network) and BERT [10] (Bidirectional Encoder Representations from Transformers) over an email data sets [11]. Ruano-Ord´as et al [12] claimed that applying automatically produced regular expressions (regex) can be one incredibly effective way to spot spammade texts that have been disguised.…”