Presentation 2021-03-02
Evaluation of Uncertain Reports by Multiple Anti-virus Engines
Kazuya Nomura, Mistuaki Akiyama, Masaki Kamizono, Takahiro Kasama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) VirusTotal is an online service that provides detection results from multiple anti-virus engines. It is used in a wide range of applications such as corporate security operations and labeling of malware data for research. However, the detection results of anti-virus engines do not always provide correct information, especially for malware that has not yet been sufficiently analyzed, and the detection results may change over time. Also, since each anti-virus engine may miss malware or detect legitimate files incorrectly, it is necessary to understand and consider the uncertainty of detection results when using VirusTotal. In this study, we collected the detection results of 2,037 malware that registered in VirusTotal over a period of four months (301,685 reports in total) and analyzed these long-term detection results to understand the change in the number of detections over time. Through this analysis, we evaluate the uncertainty of detection results. Furthermore, based on the results, we propose a method to obtain threat information from VirusTotal more accurately and efficiently.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) VirusTotal / Malware / Anti-virus Engines
Paper # ICSS2020-56
Date of Issue 2021-02-22 (ICSS)

Conference Information
Committee ICSS / IPSJ-SPT
Conference Date 2021/3/1(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Security, Trust, etc.
Chair Hiroki Takakura(NII)
Vice Chair Katsunari Yoshioka(Yokohama National Univ.) / Kazunori Kamiya(NTT)
Secretary Katsunari Yoshioka(NICT) / Kazunori Kamiya(KDDI labs.)
Assistant Keisuke Kito(Mitsubishi Electric) / Toshihiro Yamauchi(Okayama Univ.)

Paper Information
Registration To Technical Committee on Information and Communication System Security / Special Interest Group on Security Psychology and Trust
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Evaluation of Uncertain Reports by Multiple Anti-virus Engines
Sub Title (in English)
Keyword(1) VirusTotal
Keyword(2) Malware
Keyword(3) Anti-virus Engines
1st Author's Name Kazuya Nomura
1st Author's Affiliation Waseda University(Waseda Univ.)
2nd Author's Name Mistuaki Akiyama
2nd Author's Affiliation NTT Secure Platform Laboratories(NTT)
3rd Author's Name Masaki Kamizono
3rd Author's Affiliation Deloitte Tohmatsu Cyber LLC(Deloitte Tohmatsu Cyber LLC)
4th Author's Name Takahiro Kasama
4th Author's Affiliation National Institute of Information and Communications Technology(NICT)
Date 2021-03-02
Paper # ICSS2020-56
Volume (vol) vol.120
Number (no) ICSS-384
Page pp.pp.178-183(ICSS),
#Pages 6
Date of Issue 2021-02-22 (ICSS)