Electricity theft in smart grids poses a significant threat to energy security, leading to billions in financial losses and grid instability worldwide. Traditional detection methods, including hardware-based solutions and machine learning (ML) models, are often costly, reliant on labeled data, and lack scalability. Deep learning (DL) approaches, while more advanced, face challenges such as overfitting to static datasets and inefficiency in adapting to evolving consumption patterns and new cyberattacks, requiring frequent and computationally expensive retraining. In this context, we propose a novel deep learning framework, Deep Adaptive Feature Learning for Theft Detection (DAFL-TD), tailored for smart grid environments. The architecture of DAFL-TD integrates a Temporal Feature Extraction Network (TFEN), which captures temporal dependencies in electricity usage, with an Adaptive Feature Learning Network (AFLN) that leverages both labeled and unlabeled data for adaptive feature extraction and classification. The novelty of DAFL-TD lies in its ability to handle fluctuating, imbalanced data and dynamically update its feature representation without the need for extensive retraining, making it highly scalable for real-world smart grid applications. Extensive evaluations on the State Grid Corporation of China (SGCC) dataset demonstrate that DAFL-TD achieves a 13.84% improvement in AUC compared to state-of-the-art models, alongside superior precision as measured by MAP metrics. These results underline the efficacy of DAFL-TD as a robust, scalable, and efficient solution for real-time electricity theft detection, significantly enhancing the resilience and security of smart grids.
M. Ahmed et al., “Energy Theft Detection in Smart Grids: Taxonomy, Comparative Analysis, Challenges, and Future Research Directions,” IEEE/CAA Journal of Automatica Sinica, vol. 9, no. 4, pp. 578–600, Apr. 2022, doi: 10.1109/jas.2022.105404.
Z. Yan and H. Wen, “Performance Analysis of Electricity Theft Detection for the Smart Grid: An Overview,” IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1–28, 2022, doi: 10.1109/tim.2021.3127649.
X. Xia, Y. Xiao, W. Liang, and J. Cui, “Detection Methods in Smart Meters for Electricity Thefts: A Survey,” Proceedings of the IEEE, vol. 110, no. 2, pp. 273–319, Feb. 2022, doi: 10.1109/jproc.2021.3139754.
K. R. Deepa and N. Thillaiarasu, “Integrated Architecture for Smart Grid Energy Management: Deep Attention-Enhanced Sequence-to-Sequence Model with Energy-Aware Optimized Reinforcement Learning for Demand Response,” SN Computer Science, vol. 5, no. 8, Nov. 2024, doi: 10.1007/s42979-024-03305-2.
Takiddin, M. Ismail, M. Nabil, M. M. E. A. Mahmoud, and E. Serpedin, “Detecting Electricity Theft Cyber-Attacks in AMI Networks Using Deep Vector Embeddings,” IEEE Systems Journal, vol. 15, no. 3, pp. 4189–4198, Sep. 2021, doi: 10.1109/jsyst.2020.3030238.
M. M. Badr, M. I. Ibrahem, M. Mahmoud, M. M. Fouda, F. Alsolami, and W. Alasmary, “Detection of False-Reading Attacks in Smart Grid Net-Metering System,” IEEE Internet of Things Journal, vol. 9, no. 2, pp. 1386–1401, Jan. 2022, doi: 10.1109/jiot.2021.3087580.
L. J. Lepolesa, S. Achari, and L. Cheng, “Electricity Theft Detection in Smart Grids Based on Deep Neural Network,” IEEE Access, vol. 10, pp. 39638–39655, 2022, doi: 10.1109/access.2022.3166146.
Elgarhy, M. M. Badr, M. M. E. A. Mahmoud, M. M. Fouda, M. Alsabaan, and H. A. Kholidy, “Clustering and Ensemble Based Approach for Securing Electricity Theft Detectors Against Evasion Attacks,” IEEE Access, vol. 11, pp. 112147–112164, 2023, doi: 10.1109/access.2023.3318111.
Anin, M. Jahanzeb Khan, O. Abdelsalam, M. Nabil, F. Hu, and A. Alsharif, “Efficient and Privacy-Preserving ConvLSTM-Based Detection of Electricity Theft Cyber-Attacks in Smart Grids,” IEEE Access, vol. 12, pp. 153089–153104, 2024, doi: 10.1109/access.2024.3478068.
Aldegheishem, M. Anwar, N. Javaid, N. Alrajeh, M. Shafiq, and H. Ahmed, “Towards Sustainable Energy Efficiency with Intelligent Electricity Theft Detection in Smart Grids Emphasising Enhanced Neural Networks,” IEEE Access, vol. 9, pp. 25036–25061, 2021, doi: 10.1109/access.2021.3056566.
E. U. Haq, C. Pei, R. Zhang, H. Jianjun, and F. Ahmad, “Electricity-theft detection for smart grid security using smart meter data: A deep-CNN based approach,” Energy Reports, vol. 9, pp. 634–643, Mar. 2023, doi: 10.1016/j.egyr.2022.11.072.
Zhu, W. Wen, J. Li, C. Zhang, B. Zhou, and Z. Shuai, “Deep Active Learning-Enabled Cost-Effective Electricity Theft Detection in Smart Grids,” IEEE Transactions on Industrial Informatics, vol. 20, no. 1, pp. 256–268, Jan. 2024, doi: 10.1109/tii.2023.3249212.
Ismail, M. F. Shaaban, M. Naidu, and E. Serpedin, “Deep Learning Detection of Electricity Theft Cyber-Attacks in Renewable Distributed Generation,” IEEE Transactions on Smart Grid, vol. 11, no. 4, pp. 3428–3437, Jul. 2020, doi: 10.1109/tsg.2020.2973681.
D. K. R and M. M. Kodabagi, “Data Analytics Challenges and Needs in Smart Grid for Smart Energy Management,” 2024 Second International Conference on Advances in Information Technology (ICAIT), pp. 1–6, Jul. 2024, doi: 10.1109/icait61638.2024.10690834.
S. Li, W. Meng, C. Liu, and S. He, “Feature Attention Distillation Defense for Backdoor Attack in Artificial-Neural-Network-Based Electricity Theft Detection,” IEEE Internet of Things Journal, vol. 11, no. 24, pp. 39880–39889, Dec. 2024, doi: 10.1109/jiot.2024.3451449.
W. Liao et al., “Transfer Learning-Driven Electricity Theft Detection in Small-Sample Cases,” IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1–13, 2024, doi: 10.1109/tim.2024.3470061.
S. Zhu, Z. Xue, and Y. Li, “Electricity Theft Detection in Smart Grids Based on Omni-Scale CNN and AutoXGB,” IEEE Access, vol. 12, pp. 15477–15492, 2024, doi: 10.1109/access.2024.3358683.
W. Zhou et al., “Electricity Theft Detection of Residential Users With Correlation of Water and Electricity Usage,” IEEE Transactions on Industrial Informatics, vol. 20, no. 4, pp. 5339–5351, Apr. 2024, doi: 10.1109/tii.2023.3332954.
R. H, D. K R, S. B. Hosur, M. B, A. K. P, and N. V. E, “Comparative Analysis and QoS Enhancement Through Novel Feedback Architecture,” 2023 International Conference on Data Science and Network Security (ICDSNS), pp. 1–6, Jul. 2023, doi: 10.1109/icdsns58469.2023.10244875.
Zanetti, E. Jamhour, M. Pellenz, and M. Penna, “A New SVM-Based Fraud Detection Model for AMI,” Computer Safety, Reliability, and Security, pp. 226–237, 2016, doi: 10.1007/978-3-319-45477-1_18.
D. K. R, R. H, L. R, A. M, S. G, and C. S. M, “Accuracy Enhance of Smart Energy Theft Detection Using Machine Learning Classifiers,” 2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), pp. 1–6, Jun. 2024, doi: 10.1109/iciteics61368.2024.10624908.
B. C. Costa, Bruno. L. A. Alberto, A. M. Portela, M. W, and E. O.Eler, “Fraud Detection in Electric Power Distribution Networks using an Ann-Based Knowledge-Discovery Process,” International Journal of Artificial Intelligence & Applications, vol. 4, no. 6, pp. 17–23, Nov. 2013, doi: 10.5121/ijaia.2013.4602.
Z. Zheng, Y. Yang, X. Niu, H.-N. Dai, and Y. Zhou, “Wide and Deep Convolutional Neural Networks for Electricity-Theft Detection to Secure Smart Grids,” IEEE Transactions on Industrial Informatics, vol. 14, no. 4, pp. 1606–1615, Apr. 2018, doi: 10.1109/tii.2017.2785963.
Md. N. Hasan, R. N. Toma, A.-A. Nahid, M. M. M. Islam, and J.-M. Kim, “Electricity Theft Detection in Smart Grid Systems: A CNN-LSTM Based Approach,” Energies, vol. 12, no. 17, p. 3310, Aug. 2019, doi: 10.3390/en12173310.
CRediT Author Statement
The authors confirm contribution to the paper as follows:
Conceptualization: Deepa K R and Thillaiarasu N;
Methodology: Deepa K R;
Software: Thillaiarasu N;
Data Curation: Deepa K R;
Writing- Original Draft Preparation: Deepa K R and Thillaiarasu N;
Visualization: Deepa K R;
Investigation: Thillaiarasu N;
Supervision: Deepa K R;
Validation: Thillaiarasu N;
Writing- Reviewing and Editing: Deepa K R and Thillaiarasu N; All authors reviewed the results and approved the final version of the manuscript.
Acknowledgements
Author(s) thanks to Dr.Thillaiarasu N for this research completion and support.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding author
Deepa K R
School of Computing and Information Technology, REVA University, Bangalore, Karnataka, India.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Deepa K R and Thillaiarasu N, “A Novel Deep Adaptive Feature Learning Framework for Efficient Electricity Theft Detection in Smart Grids”, Journal of Machine and Computing, vol.5, no.4, pp. 2278-2291, October 2025, doi: 10.53759/7669/jmc202505177.
