Episode Based Masquerade Detection

Dash, Subrat Kumar; Reddy, Krupa Sagar; Pujari, Arun K.

doi:10.1007/11593980_19

Cited by 20 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The subsequence between two consecutive break points is an episode. In this paper, we adopt the algorithm of sequence segmentation based on voting experts [3].…”

Section: Variable Length N-grammentioning

confidence: 99%

A New Feature Selection Method for Malcodes Detection

Zhang

Shuai

2009

2009 Fifth International Conference on Information Assurance and Security

View full text Add to dashboard Cite

Most of traditional antivirus systems fail to detect unknown malcodes or variants. Data mining method solves this problem as it classifies new malcodes by matching representative features. Feature selection is a key to apply data mining to successfully detect malcodes. In this paper, we propose a method, Weighted Information Gain (WIG), which can select effective features more correctly by combining the advantages of Information Gain with feature frequency. The experiment results demonstrate that the proposed method achieves high detection and accuracy rate.

show abstract

“…The subsequence between two consecutive break points is an episode. In this paper, we adopt the algorithm of sequence segmentation based on voting experts [3].…”

Section: Variable Length N-grammentioning

confidence: 99%

A New Feature Selection Method for Malcodes Detection

Zhang

Shuai

2009

2009 Fifth International Conference on Information Assurance and Security

View full text Add to dashboard Cite

show abstract

“…Then, from the considerable number of signatures collected, the ones with lowest predicted false positive rate were selected. Assaleh et al [9] observed that n-grams extracted from byte sequences can be used as an effective feature. They used Common n-gram (CNG) as the features and proposed a k-NN classification for detecting malicious executables.…”

Section: Introductionmentioning

confidence: 99%

“…Kolter et al [7] independently realized that n-grams can possibly be used as a set of features. After variable length n-grams were previously used in intrusion detection [9][10] and text categorization [11][12] , Reddy [13] proposed a very elegant and novel method of malicious codes detection by extracting the common features of virus programs as variable length n-grams.…”

Section: Introductionmentioning

confidence: 99%

A Feature Selection for Malicious Detection

Lai

2008

2008 Ninth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed

View full text Add to dashboard Cite

The detection of unknown malicious executables is beyond the capability of many existing detection approaches. Machine learning or data mining methods can identify new or unknown malicious executables with some degree of success. Feature selection is a key to apply data mining or machine learning to successfully detect malicious executables. We propose a method to extract features which are most representative of viral properties. We show that our classifier, based on strings, achieves high detection rates and can be expected to perform as well in real-world conditions.

show abstract

“…This improves the masquerade detection performance further. We also show that the performance of our approach is better than previously used methods such as the SVM based technique [7] and the episode based Naïve Bayes technique [3]. The paper is organized as follows: Sect.…”

mentioning

confidence: 98%

“…The 'voting engine' decides if the block is to be considered as being anomalous. Dash etal [3] proposed an episode based Naïve Bayes technique. In this technique meaningful episodes are extracted from a long sequence of commands.…”

mentioning

confidence: 99%

Detecting masquerades using a combination of Naïve Bayes and weighted RBF approach

Sharma

Paliwal

2007

J Comput Virol

View full text Add to dashboard Cite

Masquerade detection by automated means is gaining widespread interest due to the serious impact of masquerades on computer system or network. Several techniques have been introduced in an effort to minimize up to some extent the risk associated with masquerade attack. In this respect, we have developed a novel technique which comprises of Naïve Bayes approach and weighted radial basis function similarity approach. The proposed scheme exhibits very promising results in comparison with many earlier techniques while experimenting on SEA dataset in detecting masquerades.

show abstract

Episode Based Masquerade Detection

Cited by 20 publications

References 11 publications

A New Feature Selection Method for Malcodes Detection

A New Feature Selection Method for Malcodes Detection

A Feature Selection for Malicious Detection

Detecting masquerades using a combination of Naïve Bayes and weighted RBF approach

Contact Info

Product

Resources

About