用Transformer模型提升无人机交通管理系统漏洞发现效率。
Revealing Safety-Critical Scenarios for UTM via Transformer
- 将漏洞探测建模为序列问题，用注意力机制捕捉系统状态关联。
- 在700小时仿真中实现漏洞发现效率提升8倍，捕获传统方法遗漏的极端场景。
- 适合研究空域安全、智能测试生成或强化学习应用的开发者。
无人航空交通管理（UTM）系统是用于远程管理多架飞行器的云平台，具有极高的安全性要求，不容许碰撞或坠毁等故障发生。然而，目前缺乏最优的故障暴露示范和明确的奖励信号来揭示潜在漏洞，且系统的自愈能力导致关键故障呈现‘长尾效应’。本文将UTM漏洞发现建模为序列建模问题，采用基于Transformer的强化学习架构。提出策略模型生成针对性测试场景，动作采样器施加领域约束，并设计基于风险的奖励函数引导探索。在700小时的仿真评估中，相比专家指导测试，漏洞发现效率提升8倍，还发现了传统方法未覆盖的关键边缘案例。
原文摘要 · Abstract (English)
Unmanned Traffic Management (UTM) systems are cloud-based platforms designed to manage and coordinate multiple aerial vehicles remotely. UTM systems are safety-critical which cannot tolerate failures like crash or collision. To reveal latent vulnerabilities, there are neither optimal failure-exposing demonstrations nor clear reward signals. Additionally, UTM's self-healing capability introduces the ``long-tail effect'' of critical failures. We propose framing UTM vulnerability discovery as a sequence modeling problem amenable to transformer-based RL architectures. Our approach leverages attention mechanisms to directly model the relationship among system states, and predict optimal actions. Our framework introduces a Policy Model that generates targeted test scenarios and an Action Sampler that enforces domain constraints. We use a risk-based reward function to guide exploration. Through extensive evaluation on a 700-hour simulation study, we demonstrate an 8$\times$ improvement in vulnerability discovery efficiency compared to expert-guided testing. It also discovers critical edge cases that traditional methods have missed.
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。