基于深度学习的空间交会相对位姿估计的鲁棒对抗攻击检测
Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvous
AI总结：
针对空间交会中基于深度学习的相对位姿估计易受对抗攻击的问题，提出基于可解释性（Shapley值）与LSTM的检测方法，仿真与实验准确率达99.21%和96.29%。
摘要：
近年来，针对自主航天器相对导航挑战的深度学习技术研究持续增长。采用这些技术可提升性能，然而，此类方法也因易受对抗攻击影响而引发对深度学习方法的可信赖性与安全性的更高担忧。在本工作中，我们提出了一种新颖的对抗攻击检测方法，用于基于深度神经网络的相对位姿估计方案，该方法基于可解释性概念。我们针对轨道交会场景开发了一种创新的相对位姿估计技术，采用我们提出的卷积神经网络（CNN），该网络从追踪器星载相机获取图像，并准确输出目标的相对位置和旋转。我们使用快速梯度符号法（FGSM）生成的对抗攻击对输入图像进行无缝扰动。随后，基于长短期记忆（LSTM）网络构建对抗攻击检测器，该网络接收来自基于CNN的位姿估计器的可解释性度量，即Shapley值，并在对抗攻击发生时标记检测。仿真结果表明，所提出的对抗攻击检测器达到了99.21%的检测准确率。随后，深度相对位姿估计器和对抗攻击检测器均在从我们实验室设计的装置捕获的真实数据上进行了测试。来自我们实验室设计装置的实验结果表明，所提出的对抗攻击检测器实现了96.29%的平均检测准确率。
英文摘要：
Research on developing deep learning techniques for autonomous spacecraft relative navigation challenges is continuously growing in recent years. Adopting those techniques offers enhanced performance. However, such approaches also introduce heightened apprehensions regarding the trustability and security of such deep learning methods through their susceptibility to adversarial attacks. In this work, we propose a novel approach for adversarial attack detection for deep neural network-based relative pose estimation schemes based on the explainability concept. We develop for an orbital rendezvous scenario an innovative relative pose estimation technique adopting our proposed Convolutional Neural Network (CNN), which takes an image from the chaser's onboard camera and outputs accurately the target's relative position and rotation. We perturb seamlessly the input images using adversarial attacks that are generated by the Fast Gradient Sign Method (FGSM). The adversarial attack detector is then built based on a Long Short Term Memory (LSTM) network which takes the explainability measure namely SHapley Value from the CNN-based pose estimator and flags the detection of adversarial attacks when acting. Simulation results show that the proposed adversarial attack detector achieves a detection accuracy of 99.21%. Both the deep relative pose estimator and adversarial attack detector are then tested on real data captured from our laboratory-designed setup. The experimental results from our laboratory-designed setup demonstrate that the proposed adversarial attack detector achieves an average detection accuracy of 96.29%.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
