Search

Cybercrime has led to the loss of billions of dollars, the malfunctioning of computer systems, the destruction of critical information, the compromising of network integrity and confidentiality, etc. In view of these crimes committed on a daily basis, the security of the computer systems has become imperative to minimize and possibly avoid the impact of cybercrimes. In this paper, we review recent advances in the use of cyber security benchmark datasets for the evaluation of machine learning and data mining-based intrusion detection systems. It was found that the state-of-the-art cyber security benchmark datasets KDD and UNM are no longer reliable, because their datasets cannot meet the expectations of current advances in computer technology. As a result, a new ADFA Linux (ADFA-LD)cyber security benchmark dataset for the evaluation of machine learning and data mining-based intrusion detection systems was proposed in 2013 to meet the current significant advances in computer technology. ADFA-LD requires improvement in terms of full descriptions of its attributes. This review can be used by the research community as a basis for abandoning the previous state-of-the-art cyber security benchmark datasets and starting to use the newly introduced benchmark dataset for effective and robust evaluation of machine learning and data mining-based intrusion detection system. [ABSTRACT FROM AUTHOR]

Cybercrime has led to the loss of billions of dollars, the malfunctioning of computer systems, the destruction of critical information, the compromising of network integrity and confidentiality, etc. In view of these crimes committed on a daily basis, the security of the computer systems has become imperative to minimize and possibly avoid the impact of cybercrimes. In this paper, we review recent advances in the use of cyber security benchmark datasets for the evaluation of machine learning and data mining-based intrusion detection systems. It was found that the state-of-the-art cyber security benchmark datasets KDD and UNM are no longer reliable, because their datasets cannot meet the expectations of current advances in computer technology. As a result, a new ADFA Linux (ADFA-LD)cyber security benchmark dataset for the evaluation of machine learning and data mining-based intrusion detection systems was proposed in 2013 to meet the current significant advances in computer technology. ADFA-LD requires improvement in terms of full descriptions of its attributes. This review can be used by the research community as a basis for abandoning the previous state-of-the-art cyber security benchmark datasets and starting to use the newly introduced benchmark dataset for effective and robust evaluation of machine learning and data mining-based intrusion detection system. [ABSTRACT FROM AUTHOR]

Abstract: Due to its simple and inherently vulnerable nature, e-mail communication is abused for numerous illegitimate purposes. E-mail spamming, phishing, drug trafficking, cyber bullying, racial vilification, child pornography, and sexual harassment are some common e-mail mediated cyber crimes. Presently, there is no adequate proactive mechanism for securing e-mail systems. In this context, forensic analysis plays a major role by examining suspected e-mail accounts to gather evidence to prosecute criminals in a court of law. To accomplish this task, a forensic investigator needs efficient automated tools and techniques to perform a multi-staged analysis of e-mail ensembles with a high degree of accuracy, and in a timely fashion. In this article, we present our e-mail forensic analysis software tool, developed by integrating existing state-of-the-art statistical and machine-learning techniques complemented with social networking techniques. In this framework we incorporate our two proposed authorship attribution approaches; one is presented for the first time in this article. [Copyright &y& Elsevier]