arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.01258cs.LG
收藏

通过鲁棒性评估和操作配置文件评估深度学习分类器的可靠性

Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles

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

Xingyu Zhao, Wei Huang, Alec Banks, Victoria Cox, David Flynn, Sven Schewe, Xiaowei Huang

摘要:

深度学习(DL)的使用正在进入越来越复杂的应用。虽然它显示出提供转型能力的巨大潜力,但DL也提出了关于其关键功能可靠性的新挑战。在本文中,我们提出了一个模型无关的可靠性评估方法的DL分类器,基于证据的鲁棒性评估和操作配置文件(OP)的一个给定的应用程序。我们将输入空间划分为小单元,然后根据OP“组装”它们的鲁棒性(到地面真值),其中提供了单元鲁棒性和OP的估计。可靠性估计的每输入误分类概率(pmi)可以与置信水平一起导出。一个原型工具演示了简化的案例研究。模型假设和扩展到现实世界的应用进行了讨论。虽然我们的模型很容易揭示评估DL可靠性的固有困难(例如缺乏具有地面真实性和可扩展性问题的数据),但我们提供了初步/折衷的解决方案来推进这一研究方向。

英文摘要:

The utilisation of Deep Learning (DL) is advancing into increasingly more sophisticated applications. While it shows great potential to provide transformational capabilities, DL also raises new challenges regarding its reliability in critical functions. In this paper, we present a model-agnostic reliability assessment method for DL classifiers, based on evidence from robustness evaluation and the operational profile (OP) of a given application. We partition the input space into small cells and then "assemble" their robustness (to the ground truth) according to the OP, where estimators on the cells' robustness and OPs are provided. Reliability estimates in terms of the probability of misclassification per input (pmi) can be derived together with confidence levels. A prototype tool is demonstrated with simplified case studies. Model assumptions and extension to real-world applications are also discussed. While our model easily uncovers the inherent difficulties of assessing the DL dependability (e.g. lack of data with ground truth and scalability issues), we provide preliminary/compromised solutions to advance in this research direction.

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。

↑