SVDD 기반 중요문서 변조 유출 탐지 알고리즘
An Algorithm for Detecting Leak of Defaced Confidential Information Based on SVDD
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This paper proposes the algorithm which addresses the problem of detecting leak of defaced confidential documents from original confidential document. Generally, a confidential document is defaced into various forms by insiders and then they are trying to leak these defaced documents to outside. Traditional algorithms detecting leak of documents have low accuracy because they are based on similarity of two documents, which do not reflect various forms of defaced documents in detection. In order to overcome this problem, this paper proposes a novel v-SVDD algorithm which is based on SVDD, the novelty detection algorithm. The result of experiment shows that there is significant improvement in the accuracy of the v-SVDD in comparison with the traditional algorithms.
Abstract
This paper proposes the algorithm which addresses the problem of detecting leak of defaced confidential documents from original confidential document. Generally, a confidential document is defaced into various forms by insiders and then they are trying to leak these defaced documents to outside. Traditional algorithms detecting leak of documents have low accuracy because they are based on similarity of two documents, which do not reflect various forms of defaced documents in detection. In order to overcome this problem, this paper proposes a novel v-SVDD algorithm which is based on SVDD, the novelty detection algorithm. The result of experiment shows that there is significant improvement in the accuracy of the v-SVDD in comparison with the traditional algorithms.
참고문헌 (9)
- 남기효, "내부정보 유출방지(DLP) 기술동향", 주간기술동향, (1413), pp.1~9 (2009), 정보통신산업진흥원
- A.Per, "Document-document similarity approaches and science mapping:Experimental comparison of five approaches", Journal of Informetrics, 3(1), pp.49~63 (2009)
- C.James, "Tightening the net:A review of current and next generation spam filtering tools", Computers & Security, 25(8), pp.566~578 (2006)
- F.Janssens, "Towards mapping library and information science", Information Processing & Management, 42(6), pp.1614~1642 (2006)
- F.Janssens, "Dynamic hybrid clustering of bioinformatics by incorporating text mining and citation analysis", Proceedings of the 13th ACM SIGKDD international conference on knowledge discovery and data mining, pp.360~369 (2007)
- G.Vladutz, "Bibliographic coupling and subject relatedness", Proceedings of the 47th ASIS annual meeting, pp.204~207 (1984)
- P.Glenisson, "Combining full text and bibliometric information in mapping scientific disciplines", Information Processing & Management, 41(6), pp.1548~1572 (2005)
- T.David, "Support vector data description", Machine Learning, 54(1), pp.45~66 (2004)
- Z. Yong, "Fuzzy multi-class classifier based on Support vector data description and improved PCM", Expert System with Applications, 36(5), pp.8714~8718 (2009)