Presentation 2015-03-04
Estimation of Vulnerability Score based on Annual Analysis with Supervised Latent Dirichlet Allocation
Yasuhiro YAMAMOTO, Daisuke MIYAMOTO, Masaya NAKAYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This research purpose is to determine technical scores of vulnerability by using machine learning methods in order to evaluate vulnerability quickly, for not rated vulnerability information. Vulnerability information datasets utilized in this research are databases composed of vulnerability descriptions and vulnerability risk evaluations. High precision of score prediction was aimed by to make evaluated value calculated from recent year's data high, and to make evaluated value calculated from past year's data low, from validation results of machine learning in training data of each year's data. As a result, higher precision than the value by just utilizing supervised latent Dirichlet allocation, was gained in 12 categories out of 18 categories. This result could enable quick vulnerability evaluation by determining scores of vulnerability in machine learning methods.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Security / Vulnerability / SLDA / CVE / CVSS
Paper # ICSS2014-79
Date of Issue

Conference Information
Committee ICSS
Conference Date 2015/2/24(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Information and Communication System Security (ICSS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Estimation of Vulnerability Score based on Annual Analysis with Supervised Latent Dirichlet Allocation
Sub Title (in English)
Keyword(1) Security
Keyword(2) Vulnerability
Keyword(3) SLDA
Keyword(4) CVE
Keyword(5) CVSS
1st Author's Name Yasuhiro YAMAMOTO
1st Author's Affiliation ()
2nd Author's Name Daisuke MIYAMOTO
2nd Author's Affiliation
3rd Author's Name Masaya NAKAYAMA
3rd Author's Affiliation
Date 2015-03-04
Paper # ICSS2014-79
Volume (vol) vol.114
Number (no) 489
Page pp.pp.-
#Pages 6
Date of Issue