FAILS: a tool for assessing risk in ML systems

被引：4

作者：

Dominguez, Gonzalo Aguirre ^{[1
]}

Kawaai, Keigo ^{[1
]}

Maruyama, Hiroshi ^{[1
]}

机构：

[1] Preferred Networks Inc, Tokyo, Japan

来源：

2021 28TH ASIA-PACIFIC SOFTWARE ENGINEERING CONFERENCE WORKSHOPS (APSECW 2021) | 2021年

关键词：

AI engineering; quality assurance; software engineering; machine learning;

D O I：

10.1109/APSECW53869.2021.00010

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

Quality assurance of AI based systems presents a unique set of challenges to software engineers, making it difficult to assess the risks involved when deploying them. We present a risk assessment tool based on the widely used failure mode effect analysis (FMEA) methodology, as well as quality assurance guidelines released in recent years. The tool aims to support the search for potential risks in machine learning (ML) components used in the design and development of AI products. A preliminary evaluation showed its effectiveness and pointed toward areas for future improvement.

引用

页码：1 / 4

页数：4

共 10 条

[1] [Anonymous], 2015, ADV NEURAL INF PROCE, DOI DOI 10.5555/2969442.2969519
[2] [Anonymous], 2019, Failure Mode and Effects Analysis. FMEA Handbook - Design and Process FMEA
[3] [Anonymous], 2020, GUID QUAL ASS AI SYS
[4] Breck E, 2017, IEEE INT CONF BIG DA, P1123, DOI 10.1109/BigData.2017.8258038
[5] Hulten G., 2018, Building Intelligent Systems: A Guide to Machine Learning Engineering
[6] Ishikawa Fuyuki, 2019, 2019 IEEE/ACM Joint 7th International Workshop on Conducting Empirical Studies in Industry (CESI) and 6th International Workshop on Software Engineering Research and Industrial Practice (SER&IP). Proceedings, P2, DOI 10.1109/CESSER-IP.2019.00009
[7] The Marabou Framework for Verification and Analysis of Deep Neural Networks
Katz, Guy
Huang, Derek A.
Ibeling, Duligur
Julian, Kyle
Lazarus, Christopher
Lim, Rachel
Shah, Parth
Thakoor, Shantanu
Wu, Haoze
Zeljic, Aleksandar
Dill, David L.
Kochenderfer, Mykel J.
Barrett, Clark
[J]. COMPUTER AIDED VERIFICATION, CAV 2019, PT I, 2019, 11561 : 443 - 452
[8] Maruyama H., 2018, P INT WORKSH EV BAS, P3
[9] Oiwa Y., 2021, MACHINE LEARNING QUA
[10] Wiegers Karl, 2013, SOFTWARE REQUIREMENT

← 1 →