# Robust Adversarial Attacks Detection based on Explainable Deep Reinforcement Learning For UAV Guidance and Planning

arXiv: https://arxiv.org/abs/2206.02670 · HTML: https://mlsanity.com/paper/2206.02670/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 6 Jun 2022.

## Builds on (most cited first, 20 of 20)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [Learning to Navigate in Complex Environments](https://mlsanity.com/paper/1611.03673/) (2016)
- [Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning](https://mlsanity.com/paper/2001.09684/) (2020)
- [Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments](https://mlsanity.com/paper/1612.05533/) (2016)
- [When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signatures](https://mlsanity.com/paper/1909.03418/) (2019)
- [Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight](https://mlsanity.com/paper/1710.00814/) (2017)
- [Online Robust Policy Learning in the Presence of Unknown Adversaries](https://mlsanity.com/paper/1807.06064/) (2018)
- [Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses](https://mlsanity.com/paper/2106.08746/) (2021)
- [Autonomous UAV Navigation: A DDPG-based Deep Reinforcement Learning Approach](https://mlsanity.com/paper/2003.10923/) (2020)

## Built on by (most cited first, 13 of 13)

- [Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunities](https://mlsanity.com/paper/2310.08565/) (2023)
- [Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing](https://mlsanity.com/paper/2507.04105/) (2025)
- [State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning](https://mlsanity.com/paper/2503.20613/) (2025)
- [Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks](https://mlsanity.com/paper/2503.20844/) (2025)
- [Benchmarking Deep Reinforcement Learning for Navigation in Denied Sensor Environments](https://mlsanity.com/paper/2410.14616/) (2024)
- [Deep Reinforcement Learning based Autonomous Decision-Making for Cooperative UAVs: A Search and Rescue Real World Application](https://mlsanity.com/paper/2502.20326/) (2025)
- [EVD4UAV: An Altitude-Sensitive Benchmark to Evade Vehicle Detection in UAV](https://mlsanity.com/paper/2403.05422/) (2024)
- [A Robust Adversary Detection-Deactivation Method for Metaverse-oriented Collaborative Deep Learning](https://mlsanity.com/paper/2401.01895/) (2023)
- [Adversarial Machine Learning Threats to Spacecraft](https://mlsanity.com/paper/2405.08834/) (2024)
- [Stochastic Path Planning in Correlated Obstacle Fields](https://mlsanity.com/paper/2509.19559/) (2025)
- [A Review of Vision-Based Vehicle Detection for UAV-Based Traffic Monitoring: Experimental Insights and Future Directions](https://mlsanity.com/paper/2608.07571/) (2026)
- [Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvous](https://mlsanity.com/paper/2311.05992/) (2023)
- [Shared Voxel-Map-Based Cooperative Indoor UAV Guidance with a Multi-Agent Soft Actor-Critic Controller](https://mlsanity.com/paper/2607.25728/) (2026)

## Abstract (arXiv)

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.