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 2401.02283cs.SEcs.LG
收藏

DEM:一种用于航空航天中深度神经网络分类器输出认证的方法

DEM: A Method for Certifying Deep Neural Network Classifier Outputs in Aerospace

The Hebrew University of Jerusalem(耶路撒冷希伯来大学);The Weizmann Institute of Science(魏茨曼科学研究所)

Guy Katz, Natan Levy, Idan Refaeli, Raz Yerushalmi

AI总结:

本文提出 DEM,一种以输出为中心、黑盒且不依赖网络拓扑的统计验证方法,用于识别航空航天 DNN 分类器中可能不可靠的单个预测,以支持安全关键场景认证。

摘要:

航空航天领域的软件开发需要遵守严格的高质量标准。虽然该领域已有针对商用软件的监管指南(例如 ARP-4754 和 DO-178),但这些指南并不适用于包含深度神经网络(DNN)组件的软件。因此,目前尚不清楚如何让航空航天系统受益于深度学习革命。我们在此开展的工作试图通过一种新颖的、以输出为中心的 DNN 认证方法来应对这一挑战。我们的方法采用统计验证技术,其关键优势在于能够标记出 DNN 输出可能不可靠的特定输入,以便随后由人类专家进行检查。为实现这一目标,我们的方法会对 DNN 针对其他邻近输入的预测进行统计分析,以检测不一致性。这与现有技术形成对比:现有技术通常尝试认证整个 DNN,而非单个输出。我们的方法将 DNN 作为黑盒使用,并且不对其拓扑结构作任何假设。我们希望这项工作构成将 DNN 集成到安全关键应用中的又一步——尤其是在航空航天领域,因为在该领域中,高质量和可靠性标准至关重要。

英文摘要:

Software development in the aerospace domain requires adhering to strict, high-quality standards. While there exist regulatory guidelines for commercial software in this domain (e.g., ARP-4754 and DO-178), these do not apply to software with deep neural network (DNN) components. Consequently, it is unclear how to allow aerospace systems to benefit from the deep learning revolution. Our work here seeks to address this challenge with a novel, output-centric approach for DNN certification. Our method employs statistical verification techniques, and has the key advantage of being able to flag specific inputs for which the DNN's output may be unreliable - so that they may be later inspected by a human expert. To achieve this, our method conducts a statistical analysis of the DNN's predictions for other, nearby inputs, in order to detect inconsistencies. This is in contrast to existing techniques, which typically attempt to certify the entire DNN, as opposed to individual outputs. Our method uses the DNN as a black-box, and makes no assumptions about its topology. We hope that this work constitutes another step towards integrating DNNs in safety-critical applications - especially in the aerospace domain, where high standards of quality and reliability are crucial.

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。

↑