Abstract
Rapid development in deep learning-based detection systems for numerous industrial applications has opened opportunities to apply them in power grids. A consumer’s power consumption can be monitored to recognize any anomalous behavior in their household. When building such detection systems, evaluating their robustness to adversarial samples is critical. It has been shown that when we provide adversarial samples to deep learning models, they falsely classify instances, even when the perturbation or noise added to the original data is very small. On the other hand, these models should be able to detect attack instances correctly and raise few to no false alarms. While this expectation can be difficult to attain, we are allowed to choose a threshold that decides the extent to which the detection and false alarm rates are compromised. To this end, we explore the threshold selection problem for state-of-the-art deep learning-based detection models such that it can recognize attack instances. We show that selecting a threshold is challenging, and even if an appropriate threshold is chosen, the tolerance of a model to adversarial samples can still leave avenues for an attack to be successful.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/. (software available from tensorflow.org)
Chahla, C., Snoussi, H., Merghem, L., Esseghir, M.: A deep learning approach for anomaly detection and prediction in power consumption data. Energy Efficiency 13(8), 1633–1651 (2020). https://doi.org/10.1007/s12053-020-09884-2
Chou, J.S., Telaga, A.S.: Real-time detection of anomalous power consumption. Renew. Sustain. Energy Rev. 33, 400–411 (2014)
Dabrowski, A., Ullrich, J., Weippl, E.R.: Grid shock: coordinated load-changing attacks on power grids: the non-smart power grid is vulnerable to cyber attacks as well. In: 33rd Annual Computer Security Applications Conference, pp. 303–314 (2017)
Fawaz, H.I., Forestier, G., Weber, J., Idoumghar, L., Muller, P.A.: Adversarial attacks on deep neural networks for time series classification. In: 2019 International Joint Conference on Neural Networks, pp. 1–8. IEEE (2019)
Gnanasambandam, A., Sherman, A.M., Chan, S.H.: Optical adversarial attack. In: IEEE/CVF International Conference on Computer Vision, pp. 92–101 (2021)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Himeur, Y., Ghanem, K., Alsalemi, A., Bensaali, F., Amira, A.: Artificial intelligence based anomaly detection of energy consumption in buildings: a review, current trends and new perspectives. Appl. Energy 287, 116601 (2021)
Hollingsworth, K., et al.: Energy anomaly detection with forecasting and deep learning. In: 2018 IEEE International Conference on Big Data, pp. 4921–4925. IEEE (2018)
Kim, T.Y., Cho, S.B.: Predicting the household power consumption using CNN-LSTM hybrid networks. In: Yin, H., Camacho, D., Novais, P., Tallón-Ballesteros, A.J. (eds.) IDEAL 2018. LNCS, vol. 11314, pp. 481–490. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-03493-1_50
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kurakin, A., Goodfellow, I.J., Bengio, S.: Adversarial examples in the physical world. In: Artificial Intelligence Safety and Security, pp. 99–112. Chapman and Hall/CRC (2018)
Li, J., Yang, Y., Sun, J.S.: Exploiting vulnerabilities of deep learning-based energy theft detection in AMI through adversarial attacks. arXiv preprint arXiv:2010.09212 (2020)
Mode, G.R., Hoque, K.A.: Adversarial examples in deep learning for multivariate time series regression. In: 2020 IEEE Applied Imagery Pattern Recognition Workshop, pp. 1–10. IEEE (2020)
Raman, G., Peng, J.C.H., Rahwan, T.: Manipulating residents’ behavior to attack the urban power distribution system. IEEE Trans. Indust. Inform. 15(10), 5575–5587 (2019)
Ren, K., Zheng, T., Qin, Z., Liu, X.: Adversarial attacks and defenses in deep learning. Engineering 6(3), 346–360 (2020)
Soltan, S., Mittal, P., Poor, H.V.: BlackIoT: IoT botnet of high wattage devices can disrupt the power grid. In: 27th USENIX Security Symposium, pp. 15–32 (2018)
Tsukada, M., Kondo, M., Matsutani, H.: A neural network-based on-device learning anomaly detector for edge devices. IEEE Trans. Comput. 69(7), 1027–1044 (2020)
Wang, X., Zhao, T., Liu, H., He, R.: Power consumption predicting and anomaly detection based on long short-term memory neural network. In: 2019 IEEE 4th International Conference on Cloud Computing and Big Data Analysis, pp. 487–491. IEEE (2019)
Weng, Y., Zhang, N., Xia, C.: Multi-agent-based unsupervised detection of energy consumption anomalies on smart campus. IEEE Access 7, 2169–2178 (2018)
Zizzo, G., Hankin, C., Maffeis, S., Jones, K.: Adversarial attacks on time-series intrusion detection for industrial control systems. In: 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications, pp. 899–910. IEEE (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Madabhushi, S., Dewri, R. (2022). On the Impact of Model Tolerance in Power Grid Anomaly Detection Systems. In: Badarla, V.R., Nepal, S., Shyamasundar, R.K. (eds) Information Systems Security. ICISS 2022. Lecture Notes in Computer Science, vol 13784. Springer, Cham. https://doi.org/10.1007/978-3-031-23690-7_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-23690-7_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23689-1
Online ISBN: 978-3-031-23690-7
eBook Packages: Computer ScienceComputer Science (R0)