mlsanityData to 14 Oct 2026

Real-Time Defense Against Coordinated Cyber-Physical Attacks: A Robust Constrained Reinforcement Learning Approach

arXiv 2509.10999 ↗First posted 13 Sep 2025eess.SY cs.SY eess.SPcited by 0

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

Abstract (arXiv)

Modern power systems face increasing vulnerability to sophisticated cyber-physical attacks beyond traditional N-1 contingency frameworks. Existing security paradigms face a critical bottleneck: efficiently identifying worst-case scenarios and rapidly coordinating defensive responses are hindered by intensive computation and time delays, during which cascading failures can propagate. This paper presents a novel tri-level robust constrained reinforcement learning (RCRL) framework for robust power system security. The framework generates diverse system states through AC-OPF formulations, identifies worst-case N-K attack scenarios for each state, and trains policies to mitigate these scenarios across all operating conditions without requiring predefined attack patterns. The framework addresses constraint satisfaction through Beta-blending projection-based feasible action mapping techniques during training and primal-dual augmented Lagrangian optimization for deployment. Once trained, the RCRL policy learns how to control observed cyber-physical attacks in real time. Validation on IEEE benchmark systems demonstrates effectiveness against coordinated N-K attacks, causing widespread cascading failures throughout the network. The learned policy can successfully respond rapidly to recover system-wide constraints back to normal within 0.21 ms inference times, establishing superior resilience for critical infrastructure protection.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 9 of its 39 references that are in the map. First posted on arXiv 13 Sep 2025.

Builds on

9 of 39 references.

References · 9

  1. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  2. 2020Distributionally Robust Chance Constrained Data-enabled Predictive Controlcited by 16
  3. 2018Cyber-Security in Smart Grid: Survey and Challengescited by 13
  4. 2021Adversarially Robust Learning for Security-Constrained Optimal Power Flowcited by 6
  5. 2020Deep Reinforcement Learning for DER Cyber-Attack Mitigationcited by 4
  6. 2017Optimal Attack against Cyber-Physical Control Systems with Reactive Attack Mitigationcited by 1
  7. 2019Performance and Resilience of Cyber-Physical Control Systems with Reactive Attack Mitigationcited by 1
  8. 2022Adam-based Augmented Random Search for Control Policies for Distributed Energy Resource Cyber Attack Mitigationcited by 1
  9. 2024Robust Optimal Power Flow Against Adversarial Attacks: A Tri-Level Optimization Approachcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024A Reinforcement Learning Engine with Reduced Action and State Space for Scalable Cyber-Physical Optimal Response
  2. 2024A Review of Safe Reinforcement Learning Methods for Modern Power Systems
  3. 2026Game-Theoretic Reinforcement Learning based Topology-Agnostic Defense for Virtual Power Plants
  4. 2024DRL2FC: An Attack-Resilient Controller for Automatic Generation Control Based on Deep Reinforcement Learning
  5. 2024Learning-Enabled Adaptive Voltage Protection Against Load Alteration Attacks On Smart Grids ↗
  6. 2025Game-Theoretic Resilience Framework for Cyber-Physical Microgrids using Multi-Agent Reinforcement Learning
  7. 2024A Novel Bifurcation Method for Observation Perturbation Attacks on Reinforcement Learning Agents: Load Altering Attacks on a Cyber Physical Power System
  8. 2024Make Safe Decisions in Power System: Safe Reinforcement Learning Based Pre-decision Making for Voltage Stability Emergency Control