Presentation 2018-06-25
Calculating Similarity between IoT Malware Samples over CPU Architectures
Ryoichi Isawa, Tao Ban, Ying Tie, Katsunari Yoshioka, Daisuke Inoue,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Malware samples infecting IoT (Internet of Things) devices such as Web cameras andhome routers have spread over the Internet. Those samples are often generated byreusing source code to run on various CPU architectures (e.g., ARM and MIPS) of IoTdevices, and they behave similar, but their binaries vary because of different ISAs(Instruction Set Architecture). Even if analysts simply compare the malware binaries, they cannot find out similar samples from their malware repository. In thispaper, we propose a method for calculating similaritybetween malware samples running on different CPU architectures. A key idea behind our method is to convert each malware binary into an intermediate representationto fill the gap between different ISAs. It then calculates their similarity based onthe intermediate representation. With experiments using twelve in-the-wild malwaresamples (Mirai-ARM/MIPS and Bashlite-ARM/MIPS samples), we evaluated effectivenessof our method. Although the number of samples was not sufficient, thispaper shows a future direction for calculating the similarity.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Internet of Things / Malware analysis / Intermediate representation / N-gram / Jaccard similarity
Paper # IA2018-2,ICSS2018-2
Date of Issue 2018-06-18 (IA, ICSS)

Conference Information
Committee ICSS / IA
Conference Date 2018/6/25(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Ehime University
Topics (in Japanese) (See Japanese page)
Topics (in English) Internet Security, etc.
Chair Yoshiaki Shiraishi(Kobe Univ.) / Katsuyoshi Iida(Hokkaido Univ.)
Vice Chair Hiroki Takakura(NII) / Katsunari Yoshioka(Yokohama National Univ.) / Rei Atarashi(IIJ) / Hiroyuki Osaki(Kwansei Gakuin Univ.) / Toru Kondo(Hiroshima Univ.)
Secretary Hiroki Takakura(NTT) / Katsunari Yoshioka(NICT) / Rei Atarashi(Tokyo Metropolitan Univ.) / Hiroyuki Osaki(TOYOTA-IT) / Toru Kondo(NEC)
Assistant Akira Yamada(KDDI labs.) / Keisuke Kito(Mitsubishi Electric) / Kenji Ohira(Tokushima Univ.) / Ryohei Banno(Tokyo Inst. of Tech.)

Paper Information
Registration To Technical Committee on Information and Communication System Security / Technical Committee on Internet Architecture
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Calculating Similarity between IoT Malware Samples over CPU Architectures
Sub Title (in English)
Keyword(1) Internet of Things
Keyword(2) Malware analysis
Keyword(3) Intermediate representation
Keyword(4) N-gram
Keyword(5) Jaccard similarity
1st Author's Name Ryoichi Isawa
1st Author's Affiliation NICT(NICT)
2nd Author's Name Tao Ban
2nd Author's Affiliation NICT(NICT)
3rd Author's Name Ying Tie
3rd Author's Affiliation Yokohama National University(YNU)
4th Author's Name Katsunari Yoshioka
4th Author's Affiliation Yokohama National University/NICT(YNU/NICT)
5th Author's Name Daisuke Inoue
5th Author's Affiliation NICT(NICT)
Date 2018-06-25
Paper # IA2018-2,ICSS2018-2
Volume (vol) vol.118
Number (no) IA-108,ICSS-109
Page pp.pp.7-12(IA), pp.7-12(ICSS),
#Pages 6
Date of Issue 2018-06-18 (IA, ICSS)