Auditing and Testing AI - A Holistic Framework

被引：0
|
作者：
Becker, Nikolas [1 ]
Waltl, Bernhard [1 ]
机构：
[1] Gesell Informat eV GI, Bonn, Germany
来源：
DIGITAL HUMAN MODELING AND APPLICATIONS IN HEALTH, SAFETY, ERGONOMICS AND RISK MANAGEMENT: HEALTH, OPERATIONS MANAGEMENT, AND DESIGN, PT II | 2022年 / 13320卷
关键词：
AI; Testing; Auditing; Safety; Fairness; Lifecycle; Framework;
D O I：
10.1007/978-3-031-06018-2_20
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
This paper describes a framework that can be used to assess and analyze AI systems in terms of risk. The framework addresses the structure and components of AI systems at five layers and allows taking a holistic view of AI systems while focusing on specific aspects, such as discrimination or data.
引用
收藏
页码：283 / 292
页数：10
相关论文
共 50 条
  • [1] A Holistic Framework for Forecasting Transformative AI
    Gruetzemacher, Ross
    BIG DATA AND COGNITIVE COMPUTING, 2019, 3 (03) : 1 - 27
  • [2] A Holistic Framework for AI Systems in Industrial Applications
    Kaymakci, Can
    Wenninger, Simon
    Sauer, Alexander
    INNOVATION THROUGH INFORMATION SYSTEMS, VOL II: A COLLECTION OF LATEST RESEARCH ON TECHNOLOGY ISSUES, 2021, 47 : 78 - 93
  • [3] A Holistic Assurance Framework for Video Endurance Testing
    Das, Debasish
    Das, Tapan
    2015 IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS), 2015, : 290 - 295
  • [4] Auditing the AI Auditors: A Framework for Evaluating Fairness and Bias in High Stakes AI Predictive Models
    Landers, Richard N.
    Behrend, Tara S.
    AMERICAN PSYCHOLOGIST, 2023, 78 (01) : 36 - 49
  • [5] A Testing Framework for AI Linguistic Systems (testFAILS)
    Kumar, Yulia
    Morreale, Patricia
    Sorial, Peter
    Delgado, Justin
    Li, J. Jenny
    Martins, Patrick
    ELECTRONICS, 2023, 12 (14)
  • [6] A Testing Framework for AI Linguistic Systems (testFAILS)
    Kumar, Y.
    Morreale, P.
    Sorial, P.
    Delgado, J.
    Li, J. Jenny
    Martins, P.
    2023 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE TESTING, AITEST, 2023, : 51 - 54
  • [7] An AI-Based Automated Continuous Compliance Awareness Framework (CoCAF) for Procurement Auditing
    Wang, Ke
    Zipperle, Michael
    Becherer, Marius
    Gottwalt, Florian
    Zhang, Yu
    BIG DATA AND COGNITIVE COMPUTING, 2020, 4 (03) : 1 - 14
  • [8] AI auditing: The Broken Bus on the Road to AI Accountability
    Birhane, Abeba
    Steed, Ryan
    Ojewale, Victor
    Vecchione, Briana
    Raji, Inioluwa Deborah
    IEEE CONFERENCE ON SAFE AND TRUSTWORTHY MACHINE LEARNING, SATML 2024, 2024, : 612 - 643
  • [9] Testing Framework for Black-box AI Models
    Aggarwal, Aniya
    Shaikh, Samiulla
    Hans, Sandeep
    Haldar, Swastik
    Ananthanarayanan, Rema
    Saha, Diptikalyan
    2021 IEEE/ACM 43RD INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING: COMPANION PROCEEDINGS (ICSE-COMPANION 2021), 2021, : 81 - 84
  • [10] Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing
    Raji, Inioluwa Deborah
    Smart, Andrew
    White, Rebecca N.
    Mitchell, Margaret
    Gebru, Timnit
    Hutchinson, Ben
    Smith-Loud, Jamila
    Theron, Daniel
    Barnes, Parker
    FAT* '20: PROCEEDINGS OF THE 2020 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, 2020, : 33 - 44
12345