False Data Injection Attack Detection in a Power Grid Using RNN
Authors:
- 1 October 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5983-5988
Abstract
Cyber attacks on Cyber Physical Systems (CPSs), especially on those critical infrastructures poses severe threat on the public security. Among them, a special kind of attack, False Data Injection (FDI), can bypass the surveillance of state-estimation-based bad data detection mechanism silently. In this paper, we exploited the strong ability of Recurrent Neural Network (RNN) on time-series prediction to recognize the potential compromised measurements. It makes our proposed method practicable in real-world scenario that no labeled data is required during all stages of algorithm. An experiment on IEEE-14 bus test system is conducted and shows a promising result that our proposed method is able to detect FDI attack with high precision and high recall.Keywords
This publication has 12 references indexed in Scilit:
- A statistical unsupervised method against false data injection attacks: A visualization-based approachExpert Systems with Applications, 2017
- Real-Time Detection of False Data Injection Attacks in Smart Grid: A Deep Learning-Based Intelligent MechanismIEEE Transactions on Smart Grid, 2017
- The 2015 Ukraine Blackout: Implications for False Data Injection AttacksIEEE Transactions on Power Systems, 2016
- Two-Channel False Data Injection Attacks Against Output Tracking Control of Networked SystemsIEEE Transactions on Industrial Electronics, 2016
- Machine Learning Methods for Attack Detection in the Smart GridIEEE Transactions on Neural Networks and Learning Systems, 2015
- Detection of Faults and Attacks Including False Data Injection Attack in Smart Grid Using Kalman FilterIEEE Transactions on Control of Network Systems, 2014
- Vulnerabilities of Smart Grid State Estimation Against False Data Injection Attack2014
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- MATPOWER: Steady-State Operations, Planning, and Analysis Tools for Power Systems Research and EducationIEEE Transactions on Power Systems, 2010
- Long Short-Term MemoryNeural Computation, 1997