安全网的适用性研究：一种用于神经网络认证的设计即安全方案
On the Applicability of Safety Nets: A Safety-By-Design Solution for Certifying Neural Networks
浏览论文内容
中文总结 AI 辅助
该研究针对航空安全关键型AI系统的认证需求，系统分析安全网中神经网络与查找表的规模权衡，确定最优架构，实现适配航空电子硬件的100%正确输出，提供可复现的开源安全网实现。
中文摘要 AI 辅助
人工智能（AI）在安全关键型航空系统中的集成对认证和部署提出了重大挑战。航空通常被视为最安全的交通方式，依赖众多安全关键型系统。对于未来基于AI的安全关键型系统，欧洲航空安全局（EASA）要求采用设计即安全（Safety-by-Design）方法，该方法可通过安全网（Safety Nets）实现，安全网结合神经网络压缩与查找表，以确保在离散化的运行设计域内实现100%正确的运行时行为。尽管安全网已被研究，但尚未对其性能特征和系统设计权衡进行全面研究。本研究首次系统分析了安全网中神经网络与查找表规模之间的权衡，通过系统比较不同架构的神经网络，确定了在保持认证合规性的同时最小化整体存储和内存需求的最优设计参数。结果表明，具有3至5个隐藏层、每个层约50至100个节点并结合独热编码（one-hot encoding）的架构实现了最佳平衡；在这些配置中，神经网络准确表示至少97%的数据，而紧凑的查找表处理剩余误差。生成的安全网将系统规模减小了近三个数量级，适配当前航空电子硬件的内存预算，同时根据EASA准则保证在整个离散化输入空间内实现100%正确输出。本研究提供了首个用于防撞系统（HCAS）和防撞告警系统（VCAS）的安全网开源实现，结果可复现，为航空领域可认证的基于AI的系统提供了实用途径，并确立安全网作为安全关键型应用中可行的设计即安全解决方案。
英文摘要
The integration of Artificial Intelligence (AI) in safety-critical aviation systems presents significant challenges for certification and deployment. Aviation, often regarded as the safest form of transportation, relies on numerous safety-critical systems. For future safety-critical AI-based systems, EASA requires a Safety-by-Design approach, which can be achieved by using Safety Nets that combine neural network compression with lookup tables to ensure 100 % correct runtime behavior across the discretized operational design domain. Although Safety Nets have been studied, no comprehensive study of their performance characteristics and system design trade-offs has been conducted. This work presents the first systematic analysis of the trade-off between neural network and lookup table size in Safety Nets. By systematically comparing neural networks with diverse architectures, this study identifies optimal design parameters that minimize overall storage and memory requirements while maintaining certification compliance. Results demonstrate that architectures with 3 to 5 hidden layers, each with approximately 50 to 100 nodes, combined with one-hot encoding, achieve the best balance. In these configurations, neural networks accurately represent at least 97 % of the data, while compact lookup tables handle the remaining errors. The resulting Safety Nets reduce the system size by almost three orders of magnitude, fitting within the memory budget of current avionics hardware while guaranteeing 100 % correct outputs across the entire discretized input space, as required by EASA guidelines. This work provides the first-ever open-source implementation of Safety Nets for HCAS and VCAS with replicable results, demonstrating a practical pathway toward certifiable AI-based systems in aviation and establishing Safety Nets as a viable Safety-by-Design solution for safety-critical applications.
