mlsanityData to 7 Oct 2026

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

arXiv 2206.02670 ↗First posted 6 Jun 2022cs.LG cs.AI cs.CRcited by 13

Not on the map. Why?

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.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 20 of its 37 references that are in the map. First posted on arXiv 6 Jun 2022.

Builds on

20 of 37 references.

References · 20

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  6. 2015Continuous control with deep reinforcement learningcited by 3,279
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2015Trust Region Policy Optimizationcited by 2,503
  9. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  10. 2016Adversarial examples in the physical worldcited by 1,762
  11. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  12. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 517
8 more
  1. 2016Learning to Navigate in Complex Environmentscited by 192
  2. 2020Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learningcited by 61
  3. 2016Deep Reinforcement Learning with Successor Features for Navigation across Similar Environmentscited by 50
  4. 2019When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signaturescited by 40
  5. 2017Detecting Adversarial Attacks on Neural Network Policies with Visual Foresightcited by 17
  6. 2018Online Robust Policy Learning in the Presence of Unknown Adversariescited by 15
  7. 2021Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defensescited by 9
  8. 2020Autonomous UAV Navigation: A DDPG-based Deep Reinforcement Learning Approachcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 5; 2026: 2.

13 papers.

Sort:

By area:

  1. 2023Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunitiescited by 9
  2. 2025Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothingcited by 9
  3. 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learningcited by 7
  4. 2025Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attackscited by 7
  5. 2024Benchmarking Deep Reinforcement Learning for Navigation in Denied Sensor Environmentscited by 3
  6. 2025Deep Reinforcement Learning based Autonomous Decision-Making for Cooperative UAVs: A Search and Rescue Real World Applicationcited by 3
  7. 2024EVD4UAV: An Altitude-Sensitive Benchmark to Evade Vehicle Detection in UAVcited by 2
  8. 2023A Robust Adversary Detection-Deactivation Method for Metaverse-oriented Collaborative Deep Learningcited by 1
  9. 2024Adversarial Machine Learning Threats to Spacecraftcited by 1
  10. 2025Stochastic Path Planning in Correlated Obstacle Fieldscited by 1
  11. 2023Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvouscited by 0
  12. 2026Shared Voxel-Map-Based Cooperative Indoor UAV Guidance with a Multi-Agent Soft Actor-Critic Controllercited by 0
1 more
  1. 2026A Review of Vision-Based Vehicle Detection for UAV-Based Traffic Monitoring: Experimental Insights and Future Directionscited by 0