arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.05311cs.LGcs.AI
收藏

基于深度神经网络的关键系统安全框架

A Safety Framework for Critical Systems Utilising Deep Neural Networks

Heriot-Watt University(赫瑞-瓦特大学);Defence Science and Technology Laboratory(国防科学与技术实验室);University of Liverpool(利物浦大学)

Xingyu Zhao, Alec Banks, James Sharp, Valentin Robu, David Flynn, Michael Fisher, Xiaowei Huang

摘要:

来自机器学习的日益复杂的数学建模过程正被用于分析复杂的数据。然而,这些模型在实际关键系统中的性能和可解释性需要对其安全使用进行严格和持续的验证。为了应对这一挑战,本文提出了一个原则性的新的安全论证框架,利用深度神经网络的关键系统。该方法允许各种形式的预测,例如,通过某些要求的未来可靠性,或对所需可靠性水平的信心。它得到了使用操作数据的贝叶斯分析以及最近用于深度学习的验证和确认技术的支持。预测是保守的-它从生命周期活动中获得的部分先验知识开始,然后确定最坏情况的预测。还确定了开放的挑战。

英文摘要:

Increasingly sophisticated mathematical modelling processes from Machine Learning are being used to analyse complex data. However, the performance and explainability of these models within practical critical systems requires a rigorous and continuous verification of their safe utilisation. Working towards addressing this challenge, this paper presents a principled novel safety argument framework for critical systems that utilise deep neural networks. The approach allows various forms of predictions, e.g., future reliability of passing some demands, or confidence on a required reliability level. It is supported by a Bayesian analysis using operational data and the recent verification and validation techniques for deep learning. The prediction is conservative -- it starts with partial prior knowledge obtained from lifecycle activities and then determines the worst-case prediction. Open challenges are also identified.

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。

↑