论文标题
学习的可靠性验证启用了车辆跟踪
Reliability Validation of Learning Enabled Vehicle Tracking
论文作者
论文摘要
本文研究了基于高分辨率大区域运动成像输入的实现动态车辆跟踪的现实学习系统的可靠性。该系统由多个神经网络组件组成 - 处理图像输入以及多个符号（Kalman滤波器）组件 - 分析已处理的信息以进行车辆跟踪。众所周知，神经网络遭受了对抗性例子的困扰，这使它们缺乏稳健性。但是，尚不清楚学习组件的对抗性示例以及如何影响整体系统级别的可靠性。通过将覆盖范围引导的神经网络测试工具与车辆跟踪系统进行集成，我们发现（1）由于存在其他组件，总体系统可以抵御某些对抗性示例，并且（2）总体系统可以通过分析深度学习组件来确定整体系统的额外不确定性。这项研究表明，需要对支持学习的系统进行新颖的验证和验证方法。
This paper studies the reliability of a real-world learning-enabled system, which conducts dynamic vehicle tracking based on a high-resolution wide-area motion imagery input. The system consists of multiple neural network components -- to process the imagery inputs -- and multiple symbolic (Kalman filter) components -- to analyse the processed information for vehicle tracking. It is known that neural networks suffer from adversarial examples, which make them lack robustness. However, it is unclear if and how the adversarial examples over learning components can affect the overall system-level reliability. By integrating a coverage-guided neural network testing tool, DeepConcolic, with the vehicle tracking system, we found that (1) the overall system can be resilient to some adversarial examples thanks to the existence of other components, and (2) the overall system presents an extra level of uncertainty which cannot be determined by analysing the deep learning components only. This research suggests the need for novel verification and validation methods for learning-enabled systems.
