mlsanityData to 14 Oct 2026

Reinforcement Learning-Based Approaches for Enhancing Security and Resilience in Smart Control: A Survey on Attack and Defense Methods

arXiv 2402.15617 ↗First posted 23 Feb 2024cs.CR cs.SY eess.SYcited by 1

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Reinforcement Learning (RL), one of the core paradigms in machine learning, learns to make decisions based on real-world experiences. This approach has significantly advanced AI applications across various domains, notably in smart grid optimization and smart home automation. However, the proliferation of RL in these critical sectors has also exposed them to sophisticated adversarial attacks that target the underlying neural network policies, compromising system integrity. Given the pivotal role of RL in enhancing the efficiency and sustainability of smart grids and the personalized convenience in smart homes, ensuring the security of these systems is paramount. This paper aims to bolster the resilience of RL frameworks within these specific contexts, addressing the unique challenges posed by the intricate and potentially adversarial environments of smart grids and smart homes. We provide a thorough review of the latest adversarial RL threats and outline effective defense strategies tailored to safeguard these applications. Our comparative analysis sheds light on the nuances of adversarial tactics against RL-driven smart systems and evaluates the defense mechanisms, focusing on their innovative contributions, limitations, and the compromises they entail. By concentrating on the smart grid and smart home scenarios, this survey equips ML developers and researchers with the insights needed to secure RL applications against emerging threats, ensuring their reliability and safety in our increasingly connected world.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 24 of its 51 references that are in the map. First posted on arXiv 23 Feb 2024.

Builds on

24 of 51 references.

References · 24

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  5. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  6. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  7. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  8. 2017A Brief Survey of Deep Reinforcement Learningcited by 483
  9. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 469
  10. 2017Deep Reinforcement Learning: An Overviewcited by 333
  11. 2017Adversarial Attacks on Neural Network Policiescited by 320
  12. 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 311
12 more
  1. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  2. 2017Detecting Adversarial Samples from Artifactscited by 245
  3. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
  4. 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 163
  5. 2016Continuous Deep Q-Learning with Model-based Accelerationcited by 157
  6. 2018SBNet: Sparse Blocks Network for Fast Inferencecited by 54
  7. 2017The Microsoft 2017 Conversational Speech Recognition Systemcited by 52
  8. 2018IDSGAN: Generative Adversarial Networks for Attack Generation against Intrusion Detectioncited by 42
  9. 2021Defense Against Reward Poisoning Attacks in Reinforcement Learningcited by 21
  10. 2023Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstructioncited by 21
  11. 2022Provable Defense against Backdoor Policies in Reinforcement Learningcited by 18
  12. 2021Decentralized Spectrum Access System: Vision, Challenges, and a Blockchain Solutioncited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defensescited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2024A Critical Review of Safe Reinforcement Learning Techniques in Smart Grid Applications
  2. 2022Security of Deep Reinforcement Learning for Autonomous Driving: A Survey
  3. 2024Learning-Enabled Adaptive Voltage Protection Against Load Alteration Attacks On Smart Grids ↗
  4. 2024A Comprehensive Survey on the Security of Smart Grid: Challenges, Mitigations, and Future Research Opportunities
  5. 2024Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
  6. 2026Utilizing Adversarial Training for Robust Voltage Control: An Adaptive Deep Reinforcement Learning Method
  7. 2024A Review of Safe Reinforcement Learning Methods for Modern Power Systems
  8. 2024Safe and Robust Reinforcement Learning: Principles and Practice