论文标题
基于可解释的深度强化学习的无人机指导和计划的强大对抗攻击检测
Robust Adversarial Attacks Detection based on Explainable Deep Reinforcement Learning For UAV Guidance and Planning
论文作者
论文摘要
对在公共场合运营的未驾驶飞机（UAV）特工的对抗攻击的危险正在增加。采用基于AI的技术，更具体地说，深度学习（DL）方法来控制和指导这些无人机在性能方面可能是有益的，但可能会增加对这些技术的安全性及其对对抗性攻击的脆弱性的担忧。这些攻击引起的代理商决策过程中的混乱会严重影响无人机的安全性。本文提出了一种基于DL方法的解释性来建立有效检测器的创新方法，该方法将保护这些DL方案，而无人机采用它们免受攻击。代理商采用深入的增强学习（DRL）计划进行指导和计划。该代理商经过深入的确定性政策梯度（DDPG）的培训，并具有优先的经验重播（PER）DRL计划，该计划利用人工潜在领域（APF）来改善训练时间和避免障碍的绩效。建立了用于无人机可解释的基于DRL的计划和指导的模拟环境，包括障碍和对抗性攻击。对抗性攻击是通过基本迭代方法（BIM）算法产生的，并将障碍物课程的完成率从97 \％降低到35 \％。提出了两个对抗攻击探测器来应对这种减少。第一个是卷积神经网络对抗探测器（CNN-AD），它在检测80 \％时达到了准确性。第二个检测器利用长期内存（LSTM）网络。与CNN-AD相比，它具有更快的计算时间的精度为91 \％，从而可以实时对抗检测。
The dangers of adversarial attacks on Uncrewed Aerial Vehicle (UAV) agents operating in public are increasing. Adopting AI-based techniques and, more specifically, Deep Learning (DL) approaches to control and guide these UAVs can be beneficial in terms of performance but can add concerns regarding the safety of those techniques and their vulnerability against adversarial attacks. Confusion in the agent's decision-making process caused by these attacks can seriously affect the safety of the UAV. This paper proposes an innovative approach based on the explainability of DL methods to build an efficient detector that will protect these DL schemes and the UAVs adopting them from attacks. The agent adopts a Deep Reinforcement Learning (DRL) scheme for guidance and planning. The agent is trained with a Deep Deterministic Policy Gradient (DDPG) with Prioritised Experience Replay (PER) DRL scheme that utilises Artificial Potential Field (APF) to improve training times and obstacle avoidance performance. A simulated environment for UAV explainable DRL-based planning and guidance, including obstacles and adversarial attacks, is built. The adversarial attacks are generated by the Basic Iterative Method (BIM) algorithm and reduced obstacle course completion rates from 97\% to 35\%. Two adversarial attack detectors are proposed to counter this reduction. The first one is a Convolutional Neural Network Adversarial Detector (CNN-AD), which achieves accuracy in the detection of 80\%. The second detector utilises a Long Short Term Memory (LSTM) network. It achieves an accuracy of 91\% with faster computing times compared to the CNN-AD, allowing for real-time adversarial detection.
