Presentation 2021-06-22
Feature analysis of phishing website and phishing detection based on machine learning algorithms
Yi Wei, Yuji Sekiya,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Phishing is a kind of cybercrime that uses disguised websites to trick people into providing personally sensitive information. Machine Learning is a branch of Artificial Intelligence (AI), which can learn from datasets and make predictions with minimal human intervention. Phishing detection is a typical binary classification task that can be predicted by machine learning algorithms. This paper analyzes 111 features of the latest phishing websites dataset,which includes 27998 legitimate websites and 30647 phishing websites to investigate the obvious differences and correlations between phishing and legitimate websites. Then, seven commonly used machine learning algorithms are compared to detect phishing websites, including Logistic Regression, Linear Discriminant Analysis, Classification and Regression Tree, Support Vector Machine (SVM), Na?ve Bayes Classifier, Random Forest, and K-Nearest Neighbor. Among these algorithms, Random Forest shows the highest accuracy and the best performance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Cyber Security / Feature Analysis / Phishing Website Detection / Machine Learning
Paper # IA2021-9,ICSS2021-9
Date of Issue 2021-06-14 (IA, ICSS)

Conference Information
Committee IA / ICSS
Conference Date 2021/6/21(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Internet Security, etc.
Chair Tomoki Yoshihisa(Osaka Univ.) / Katsunari Yoshioka(Yokohama National Univ.)
Vice Chair Toru Kondo(Hiroshima Univ.) / Yuichiro Hei(KDDI Research) / Hiroshi Yamamoto(Ritsumeikan Univ.) / Kazunori Kamiya(NTT) / Takahiro Kasama(NICT)
Secretary Toru Kondo(Osaka Univ.) / Yuichiro Hei(Kogakuin Univ.) / Hiroshi Yamamoto(NEC) / Kazunori Kamiya(KDDI labs.) / Takahiro Kasama(Mitsubishi Electric)
Assistant Daisuke Kotani(Kyoto Univ.) / Ryo Nakamura(Fukuoka Univ.) / Daiki Nobayashi(Kyushu Inst. of Tech.) / Toshihiro Yamauchi(Okayama Univ.) / Takeshi Sugawara(Univ. of Electro-Communications)

Paper Information
Registration To Technical Committee on Internet Architecture / Technical Committee on Information and Communication System Security
Language ENG-JTITLE
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Feature analysis of phishing website and phishing detection based on machine learning algorithms
Sub Title (in English)
Keyword(1) Cyber Security
Keyword(2) Feature Analysis
Keyword(3) Phishing Website Detection
Keyword(4) Machine Learning
1st Author's Name Yi Wei
1st Author's Affiliation The University of Tokyo(Todai)
2nd Author's Name Yuji Sekiya
2nd Author's Affiliation The University of Tokyo(Todai)
Date 2021-06-22
Paper # IA2021-9,ICSS2021-9
Volume (vol) vol.121
Number (no) IA-68,ICSS-69
Page pp.pp.44-49(IA), pp.44-49(ICSS),
#Pages 6
Date of Issue 2021-06-14 (IA, ICSS)