学習ベース車両追跡システムの信頼性検証
Reliability Validation of Learning Enabled Vehicle Tracking
広域動画からの車両追跡システムに対し、カバレッジ誘導型の敵対的テストを適用し、システム全体の信頼性が個々の深層学習部品だけでは決まらないことを示した研究。
著者: Youcheng Sun, Yifan Zhou, Simon Maskell, James Sharp, Xiaowei Huang
分類: cs.CV, cs.RO
原文アブストラクト
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.
