arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.16220cs.LGcs.AIcs.CV
收藏

学习机器学习组件的运行时安全监控器

Learning Run-time Safety Monitors for Machine Learning Components

University of York(约克大学);University of Oxford(牛津大学)

Ozan Vardal, Richard Hawkins, Colin Paterson, Chiara Picardi, Daniel Omeiza, Lars Kunze, Ibrahim Habli

AI总结:

针对自主系统中机器学习组件部署后环境变化下的运行时安全监控难题,提出利用退化数据集和机器学习构建并行安全监控器的方法,并通过公开限速标志数据集的初步实验验证了可行性。

摘要:

对于作为自主系统(AS)组成部分、用于执行关键任务的机器学习组件而言,在部署后出现变化(例如系统运行环境的变化)时仍能保障模型的可靠性至关重要。其中的关键环节在于,能够在运行时监控模型性能(因变化导致)何时会对系统构成安全风险。当运行时无法获取真实标签(ground truth)时,这一挑战尤为艰巨。本文提出了一种利用退化数据集和机器学习为ML组件构建安全监控器的流程。所构建的安全监控器将与ML组件并行部署到自主系统(AS)中,用于预测与模型输出相关的安全风险。我们通过使用公开可用的限速标志数据集开展的初步实验,验证了该方法的可行性。

英文摘要:

For machine learning components used as part of autonomous systems (AS) in carrying out critical tasks it is crucial that assurance of the models can be maintained in the face of post-deployment changes (such as changes in the operating environment of the system). A critical part of this is to be able to monitor when the performance of the model at runtime (as a result of changes) poses a safety risk to the system. This is a particularly difficult challenge when ground truth is unavailable at runtime. In this paper we introduce a process for creating safety monitors for ML components through the use of degraded datasets and machine learning. The safety monitor that is created is deployed to the AS in parallel to the ML component to provide a prediction of the safety risk associated with the model output. We demonstrate the viability of our approach through some initial experiments using publicly available speed sign datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑