Robust Electricity Theft Detection Against Data Poisoning Attacks in Smart Grids

Data-driven electricity theft detectors rely on customers’ reported energy consumption readings to detect malicious behavior. One common implicit assumption in such detectors is the correct labeling of the training data. Unfortunately, these detectors are vulnerable against data poisoning attacks that assume false labels during training. This article addresses three major problems: What is the impact of data poisoning attacks on the detector’s performance? Which detector is more robust against data poisoning attacks, i.e., generalized or customer-specific detectors? How to improve the detector’s robustness against data poisoning attacks? Our investigations reveal that: (a) Shallow and deep learning-based detectors suffer from data poisoning attacks that may lead to a significant deterioration of detection rate of up to 17%. Furthermore, deep detectors offer 12% performance improvement over shallow detectors. (b) Generalized detectors present 4% performance improvement over customer-specific detectors even in the presence of data poisoning attacks. To enhance the detectors’ robustness against data poisoning attacks, we propose a sequential ensemble detector based on a deep auto-encoder with attention (AEA), gated recurrent units (GRUs), and feed forward neural networks. The proposed robust detector retains a stable detection performance that is deteriorated only by 1 – 3% in the presence of strong data poisoning attacks.

[1]  Mostafa F. Shaaban,et al.  Efficient detection of electricity theft cyber attacks in AMI networks , 2018, 2018 IEEE Wireless Communications and Networking Conference (WCNC).

[2]  Neeraj Kumar,et al.  Decision Tree and SVM-Based Data Analytics for Theft Detection in Smart Grid , 2016, IEEE Transactions on Industrial Informatics.

[3]  Chang Liu,et al.  Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning , 2018, 2018 IEEE Symposium on Security and Privacy (SP).

[4]  Ting-Wei Sun,et al.  Sparse Autoencoder with Attention Mechanism for Speech Emotion Recognition , 2019, 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS).

[5]  Victor C. M. Leung,et al.  Electricity Theft Detection in AMI Using Customers’ Consumption Patterns , 2016, IEEE Transactions on Smart Grid.

[6]  Jinkuan Wang,et al.  Electricity Theft Detection in Power Grids with Deep Learning and Random Forests , 2019, J. Electr. Comput. Eng..

[7]  Bo Tang,et al.  Detection of Electricity Theft in Customer Consumption Using Outlier Detection Algorithms , 2018, 2018 1st International Conference on Data Intelligence and Security (ICDIS).

[8]  Luis Muñoz-González,et al.  Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection , 2018, ArXiv.

[9]  Nadeem Javaid,et al.  CNN and GRU based Deep Neural Network for Electricity Theft Detection to Secure Smart Grid , 2020, 2020 International Wireless Communications and Mobile Computing (IWCMC).

[10]  Gang Hua,et al.  Electricity Theft Detection Model for Smart Meter Based on Residual Neural Network , 2020, 2020 12th IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC).

[11]  David A. Clifton,et al.  A review of novelty detection , 2014, Signal Process..

[12]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[13]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[14]  William H. Sanders,et al.  Evaluating Detectors on Optimal Attack Vectors That Enable Electricity Theft and DER Fraud , 2018, IEEE Journal of Selected Topics in Signal Processing.

[15]  Ding Xiao,et al.  Electricity Theft Detection Using Deep Bidirectional Recurrent Neural Network , 2020, 2020 22nd International Conference on Advanced Communication Technology (ICACT).

[16]  Liming Wang,et al.  AdaBoost-SVM for Electrical Theft Detection and GRNN for Stealing Time Periods Identification , 2018, IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society.

[17]  Hui Shi,et al.  Telecom Fraud Identification Based on ADASYN and Random Forest , 2020, 2020 5th International Conference on Computer and Communication Systems (ICCCS).

[18]  Erchin Serpedin,et al.  Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[19]  Patrick P. K. Chan,et al.  L-GEM based robust learning against poisoning attack , 2015, 2015 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR).

[20]  Jianhua Tao,et al.  Automatic Assessment of Depression From Speech via a Hierarchical Attention Transfer Network and Attention Autoencoders , 2020, IEEE Journal of Selected Topics in Signal Processing.

[21]  Erchin Serpedin,et al.  Deep Learning Detection of Electricity Theft Cyber-Attacks in Renewable Distributed Generation , 2020, IEEE Transactions on Smart Grid.

[22]  Erchin Serpedin,et al.  Deep Learning-Based Detection of Electricity Theft Cyber-Attacks in Smart Grid AMI Networks , 2019, Deep Learning Applications for Cyber Security.

[23]  Daria S. Lavrova,et al.  Using GRU neural network for cyber-attack detection in automated process control systems , 2019, 2019 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom).

[24]  William H. Sanders,et al.  ARIMA-Based Modeling and Validation of Consumption Readings in Power Grids , 2015, CRITIS.

[25]  Chao-Lin Kuo,et al.  Non-Cooperative Game Model Applied to an Advanced Metering Infrastructure for Non-Technical Loss Screening in Micro-Distribution Systems , 2014, IEEE Transactions on Smart Grid.