arXiv：cs.AI· Joshua Owotogbe, Roya Nasiri, Indika Kumara, Damian Andrew Tamburri, Willem-Jan van den Heuvel·· 16 小时前
AI 鲁棒性审计的可操作元需求研究
Actionable Meta-Requirements for AI Robustness Auditing
AI 导读
研究通过系统性文献综述从 2,890 篇文献中保留 74 篇，提炼出 16 个类别下的 43 项元需求，并经 128 名从业者评估获得 5,504 条评分和 586 条实质性评论，其中 81.20% 表示同意或强烈同意。
正文
Abstract:AI-enabled systems must remain dependable when the conditions under which they operate change (e.g., due to input perturbations, distribution shifts, or changes in external dependencies). This makes robustness auditing of such systems important for judging whether the available evidence is sufficient to support a defined robustness conclusion. However, designing an AI robustness auditing framework is challenging. A key unresolved issue is determining the requirements such a framework should support; these requirements have not yet been consolidated. We address this gap through meta-requirements: higher-order requirements specifying what a class of auditing frameworks should support. In design science research, literature and domain experts are common sources of meta-requirements; accordingly, we derive the initial set from literature and validate and refine it with practitioners. Our systematic literature review retained 74 of 2,890 records and derived 43 meta-requirements across 16 categories. We evaluated them with 128 practitioners, obtaining 5,504 ratings and 586 substantive comments. Overall, 81.20% of ratings indicated agreement or strong agreement. In particular, 41 of the 43 literature-derived meta-requirements were classified as strongly supported. Practitioner feedback refined the requirements and identified an additional requirement concerning external components and supply chain dependencies. The final set comprises 44 meta-requirements across 16 categories, of which 43 received quantitative validation. These meta-requirements can help organizations implement AI robustness auditing frameworks, assess existing frameworks for completeness, and refine them.
| Subjects: | Artificial Intelligence (cs.AI); Software Engineering (cs.SE) |
| Cite as: | arXiv:2610.14356 [cs.AI] |
| (or arXiv:2610.14356v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14356 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Joshua Owotogbe [view email]
[v1]
Fri, 9 Oct 2026 22:01:19 UTC (1,672 KB)
来源：arXiv：cs.AI · arxiv.org