Security Risks of Machine Learning Systems and Taxonomy Based on the Failure Mode Approach

Kazutoshi Kan
Additional contact information
Kazutoshi Kan: Deputy Director, Institute for Monetary and Economic Studies, Bank of Japan (E-mail: kazutoshi.kan@boj.or.jp)

No 21-E-03, IMES Discussion Paper Series from Institute for Monetary and Economic Studies, Bank of Japan

Abstract: This paper clarifies the source of difficulties in machine learning security and determines the usefulness of the failure mode approach for capturing security risks of machine learning systems comprehensively. Machine learning is an inductive methodology that automatically extracts relationships among data from a huge number of input-output samples. Recently, machine learning systems have been implemented deeply in various IT systems and their social impact has been increasing. However, machine learning models have specific vulnerabilities and relevant security risks that conventional IT systems do not have. An overall picture regarding these vulnerabilities and risks has not been clarified sufficiently, and there has been no consensus about their taxonomy. Thus, this paper reveals the specificity of the security risks and describes their failure modes hierarchically by classifying them on three axes, i.e., (1) presence or absence of attacker's intention, (2) location of the vulnerabilities, and (3) functional characteristics to be lost. This paper also considers points for future utilization of machine learning in society.

Keywords: Machine learning; Failure mode; Secuirty risk; Vulnerability (search for similar items in EconPapers)
JEL-codes: L86 L96 M15 Z00 (search for similar items in EconPapers)
Date: 2021-05
New Economics Papers: this item is included in nep-big
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.imes.boj.or.jp/research/papers/english/21-E-03.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ime:imedps:21-e-03

Access Statistics for this paper

More papers in IMES Discussion Paper Series from Institute for Monetary and Economic Studies, Bank of Japan Contact information at EDIRC.
Bibliographic data for series maintained by Kinken ().