梳理航空领域AI认证的挑战与路径，强调仅靠性能指标不够
Towards certifiable AI in aviation: landscape, challenges, and opportunities
- 构建航空AI形式化认证的全景思维导图
- 通过实例说明传统性能指标无法满足安全认证需求
- 适合关注航空AI安全与合规的研究者与工程师
人工智能方法在多个领域具有强大能力，尤其在航电等关键系统中，需通过认证以保证可接受的安全水平。对于安全关键系统，通用解决方案必须回答三个核心问题：是否适用？决策依据为何？对错误或攻击是否鲁棒？这一要求在AI系统中比传统方法更为复杂。本文提出航空领域形式化AI认证的综合性思维导图，重点分析认证过程中面临的挑战，并通过具体案例强调：仅依赖性能指标不足以实现合格评定，还需更全面的验证机制。
原文摘要 · Abstract (English)
Artificial Intelligence (AI) methods are powerful tools for various domains, including critical fields such as avionics, where certification is required to achieve and maintain an acceptable level of safety. General solutions for safety-critical systems must address three main questions: Is it suitable? What drives the system's decisions? Is it robust to errors/attacks? This is more complex in AI than in traditional methods. In this context, this paper presents a comprehensive mind map of formal AI certification in avionics. It highlights the challenges of certifying AI development with an example to emphasize the need for qualification beyond performance metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。