用知识图谱识别并解释自动驾驶中罕见故障，提升系统安全性。
Context-Awareness and Interpretability of Rare Occurrences for Discovery and Formalization of Critical Failure Modes
- 基于本体论构建人机协作框架，自动发现模型异常
- 在自动驾驶场景中识别出3类关键失效模式，生成可共享的知识图谱
- 适合安全评估、可信AI研究者及系统测试工程师使用
视觉系统在监控、执法和交通等关键领域应用日益广泛，但其对罕见或意外场景的脆弱性带来重大安全风险。为应对这一挑战，本文提出上下文感知与罕见事件可解释性框架CAIRO，一种基于本体论的人机协同故障发现与形式化方法，用于检测和定义关键现象（CP）。CAIRO通过激励人机协同，对人工智能黑箱模型中的误检、对抗攻击和幻觉等问题进行关键性评估。通过对自动驾驶系统（ADS）中目标检测模型的稳健分析，揭示了摄像头感知与真实环境之间的差距，并以显式知识图谱（OWL/XML格式）形式存储测试用例，支持共享、下游分析、逻辑推理与责任追溯。
原文摘要 · Abstract (English)
Vision systems are increasingly deployed in critical domains such as surveillance, law enforcement, and transportation. However, their vulnerabilities to rare or unforeseen scenarios pose significant safety risks. To address these challenges, we introduce Context-Awareness and Interpretability of Rare Occurrences (CAIRO), an ontology-based human-assistive discovery framework for failure cases (or CP - Critical Phenomena) detection and formalization. CAIRO by design incentivizes human-in-the-loop for testing and evaluation of criticality that arises from misdetections, adversarial attacks, and hallucinations in AI black-box models. Our robust analysis of object detection model(s) failures in automated driving systems (ADS) showcases scalable and interpretable ways of formalizing the observed gaps between camera perception and real-world contexts, resulting in test cases stored as explicit knowledge graphs (in OWL/XML format) amenable for sharing, downstream analysis, logical reasoning, and accountability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。