Machine Learning Methods for Attack Detection in the Smart Grid

Abstract

Attack detection problems in the smart grid are posed as statistical learning problems for different attack scenarios in which the measurements are observed in batch or online settings. In this approach, machine learning algorithms are used to classify measurements as being either secure or attacked. An attack detection framework is provided to exploit any available prior knowledge about the system and surmount constraints arising from the sparse structure of the problem in the proposed approach. Well-known batch and online learning algorithms (supervised and semi-supervised) are employed with decision and feature level fusion to model the attack detection problem. The relationships between statistical and geometric properties of attack vectors employed in the attack scenarios and learning algorithms are analyzed to detect unobservable attacks using statistical learning methods. The proposed algorithms are examined on various IEEE test systems. Experimental analyses show that machine learning algorithms can detect attacks with performances higher than the attack detection algorithms which employ state vector estimation methods in the proposed attack detection framework.

14 pages, 11 Figures

References in corpus (1)

• Sparse Attack Construction and State Estimation in the Smart Grid: Centralized and Distributed Models

Cited by in corpus (33)

• Towards Massive Machine Type Communications in Ultra-Dense Cellular IoT Networks: Current Issues and Machine Learning-Assisted Solutions
• Real-Time Detection of Hybrid and Stealthy Cyber-Attacks in Smart Grid
• Cyber-Physical Systems Security: a Systematic Mapping Study
• Joint Detection and Localization of Stealth False Data Injection Attacks in Smart Grids using Graph Neural Networks
• Security Aspects of Internet of Things aided Smart Grids: a Bibliometric Survey
• Multi-Source Data Fusion for Cyberattack Detection in Power Systems
• IoTDevID: A Behavior-Based Device Identification Method for the IoT
• Machine and Deep Learning for IoT Security and Privacy: Applications, Challenges, and Future Directions
• IoT Security Techniques Based on Machine Learning
• A Detection Mechanism Against Load-Redistribution Attacks in Smart Grids
• A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning
• Design and Evaluation of A Cyber-Physical Resilient Power System Testbed
• Method for Extracting Patterns of Coordinated Network Attacks on Electric Power CPS based on Temporal-Topological Correlation
• Finite Versus Infinite Neural Networks: an Empirical Study
• Hybrid data-driven physics model-based framework for enhance cyber-physical smart grid security
• Active and Passive Hybrid Detection Method for Power CPS False Data Injection Attacks with Improved AKF and GRU-CNN
• On the Use of Reinforcement Learning for Attacking and Defending Load Frequency Control
• ConAML: Constrained Adversarial Machine Learning for Cyber-Physical Systems
• A System-level Behavioral Detection Framework for Compromised CPS Devices: Smart-Grid Case
• PowerFDNet: Deep Learning-Based Stealthy False Data Injection Attack Detection for AC-model Transmission Systems
• A Deep Learning based Detection Method for Combined Integrity-Availability Cyber Attacks in Power System
• Machine Learning for Intelligent Authentication in 5G-and-Beyond Wireless Networks
• Cybersecurity for Modern Smart Grid against Emerging Threats
• Towards Adversarial-Resilient Deep Neural Networks for False Data Injection Attack Detection in Power Grids
• A Taxonomy of Cyber Defence Strategies Against False Data Attacks in Smart Grid
• Cyber-Physical Microgrids: Toward Future Resilient Communities
• Attack-Resilient Weighted ${\ell }_1$ Observer with Prior Pruning
• Dynamic Anomaly Detection with High-fidelity Simulators: A Convex Optimization Approach
• Simultaneous Distributed Estimation and Attack Detection/Isolation in Social Networks: Structural Observability, Kronecker-Product Network, and Chi-Square Detector
• Intelligent GPS Spoofing Attack Detection in Power Grids
• Modeling and Detection of Future Cyber-Enabled DSM Data Attacks using Supervised Learning
• Quickest Attack Detection in Smart Grid Based on Sequential Monte Carlo Filtering
• Information Theoretic Data Injection Attacks with Sparsity Constraints