Architecture of Adaptive Spam Filtering Based on Machine Learning Algorithms

Islam, Rafiqul; Zhou, Wanlei

doi:10.1007/978-3-540-72905-1_41

“…The sender's email address within an email can be faked, allowing intruders to easily bypass black-lists. According to the research in reference (Islam and Zhou, 2007;Bergholz et al, 2008) the authors noted that although the non-classification based filtering can achieve substantial performance, this method often has a high rate of false positives, making it quite risky to use on its own, as a standard stand-alone filtering system. Although our approach differs from the blacklist-based approaches, the proposed approach will complement the existing approaches as email is the primary channel for phishers to reach victims.…”

Section: Non-classification Algorithmsmentioning

confidence: 96%

“…Given that classification algorithms outperform other methods, when used in text classification (TC) (Islam and Zhou, 2007) and other classification areas like biometric recognition and image classification (Islam and Zhou, 2007;Islam et al, 2009;Fette et al, 2007), researchers are also drawn to its uses for phishing email filtering.…”

Section: Classification Algorithmsmentioning

confidence: 99%

“…Phishing protection, 2007;Netcraft, 2007;Moore and Clayton, 2007). According to the literature, classification method is considered one of the standard and commonly accepted methods to stop phishing email (Islam and Zhou, 2007;DeLong et al, 1988;André et al, 2010;Yu et al, 2009;Beck and Zhan, 2010;Liping et al, 2009;Hamid and Abawajy, 2011;Crain et al, 2010;Neville and Horie, 2011;Toolan and Carthy, 2009;Shahriar and Zulkernine, 2011;Huang et al, 2009;Haijun et al, 2011;Kim and Huh, 2011;Fu et al, 2006;Toolan and Carthy, 2010;L'Huillier and Weber, 2009;Abu-Nimeh et al, 2007;Miyamoto et al, 2009;Fette et al, 2007;He et al, 2011;Vishwanath et al, 2011;AlMomani et al, 2011). This method is effective for the currently encountered types of phishing email.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A multi-tier phishing detection and filtering approach

Islam

¹

,

Abawajy

²

2013

Journal of Network and Computer Applications

View full text Add to dashboard Cite

“…One is User selection technique and another is sender verification technique [12]. The flow diagram of the analyser is shown in the figure 5.…”

Section: Analysis Of Gl Emailsmentioning

confidence: 99%

Email Categorization Using Multi-stage Classification Technique

Islam

¹

,

Zhou

²

2007

Eighth International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT 2007)

Self Cite

View full text Add to dashboard Cite

This paper presents an innovative email categorization using a serialized multi-stage classification ensembles technique. Many approaches are used in practice for email categorization to control the menace of spam emails in different ways. Contentbased email categorization employs filtering techniques using classification algorithms to learn to predict spam e-mails given a corpus of training e-mails. This process achieves a substantial performance with some amount of FP tradeoffs. It has been studied and investigated with different classification algorithms and found that the outputs of the classifiers vary from one classifier to another with same email corpora. In this paper we have proposed a multi-stage classification technique using different popular learning algorithms with an analyser which reduces the FP (false positive) problems substantially and increases classification accuracy compared to similar existing techniques.

show abstract

“…It also minimizes what we know about human limitations, for example, memory and complex computations. Welldesigned interface reduces errors, training time and costs [5,6,10,12]. This paper proposes an effective and efficient email categorization using a multi-stage classification ensembles technique.…”

Section: Introductionmentioning

confidence: 99%

Email Categorization Using Multi-stage Classification Technique

Ren

¹

,

Gu

²

2007

Eighth International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT 2007)

Self Cite

5

0

View full text Add to dashboard Cite

This paper presents an innovative email categorization using a serialized multi-stage classification ensembles technique. Many approaches are used in practice for email categorization to control the menace of spam emails in different ways. Contentbased email categorization employs filtering techniques using classification algorithms to learn to predict spam e-mails given a corpus of training e-mails. This process achieves a substantial performance with some amount of FP tradeoffs. It has been studied and investigated with different classification algorithms and found that the outputs of the classifiers vary from one classifier to another with same email corpora. In this paper we have proposed a multi-stage classification technique using different popular learning algorithms with an analyser which reduces the FP (false positive) problems substantially and increases classification accuracy compared to similar existing techniques.

show abstract

Architecture of Adaptive Spam Filtering Based on Machine Learning Algorithms

Cited by 17 publications

References 5 publications

A multi-tier phishing detection and filtering approach

A multi-tier phishing detection and filtering approach

Email Categorization Using Multi-stage Classification Technique

Email Categorization Using Multi-stage Classification Technique

Contact Info

Product

Resources

About