Abstract
Forecasting methods typically assume clean and legitimate data streams. However, adversaries’ manipulation of digital data streams could alter the performance of forecasting algorithms and impact decision quality. In order to address such challenges, we propose a dynamic data driven application systems (DDDAS) based decision making framework that includes an adversarial forecasting component. Our framework utilizes the adversarial risk analysis principles that allow considering incomplete information and uncertainty. It is demonstrated using a load forecasting example. We solve the adversary’s decision problem in which he poisons data to alter an auto regressive forecasting algorithm output, and discuss defender strategies addressing the attack impact.
This work is supported by Air Force Scientific Office of Research (AFOSR) award FA-9550-21-1-0239 and AFOSR European Office of Aerospace Research and Development award FA8655-21-1-7042. J.M.C. is supported by a fellowship from ”la Caixa” Foundation (ID100010434), whose code is LCF/BQ/DI21/11860063. Any opinions, findings, and conclusions or recommendations expressed are those of the authors and do not necessarily reflect the views of the sponsors.
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
- 1.
Available at www.ercot.com.
References
Alfeld, S., Zhu, X., Barford, P.: Data poisoning attacks against autoregressive models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)
Alfeld, S., Zhu, X., Barford, P.: Explicit defense actions against test-set attacks. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)
Barreto, C., Koutsoukos, X.: Design of load forecast systems resilient against cyber-attacks. In: Alpcan, T., Vorobeychik, Y., Baras, J., Dan, G. (eds.) Decision and Game Theory for Security. Lecture Notes in Computer Science(), vol. 11836, pp. 1–20. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32430-8_1
Blasch, E., Ravela, S., Aved, A.: Handbook of Dynamic Data Driven Applications Systems. Springer, Cham (2018)
Brückner, M., Kanzow, C., Scheffer, T.: Static prediction games for adversarial learning problems. J. Mach. Learn. Res. 13(1), 2617–2654 (2012)
Brückner, M., Scheffer, T.: Stackelberg games for adversarial prediction problems. In: Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 547–555 (2011)
Caballero, W.N., Friend, M., Blasch, E.: Adversarial machine learning and adversarial risk analysis in multi-source command and control. Sig. Proc., Sens./Inf. Fus. Target Recogn. XXX 11756, 98–108 (2021)
Caballero, W.N., Lunday, B.J., Deckro, R.F., Pachter, M.N.: Informing national security policy by modeling adversarial inducement and its governance. Socioecon. Plann. Sci. 69, 100709 (2020)
Caballero, W.N., Camacho, J.M., Ekin, T., Naveiro, R.: Manipulating hidden-Markov-model inferences by corrupting batch data. Comput. Oper. Res. 162, 106478 (2024)
Chen, Y., Zhu, X.: Optimal attack against autoregressive models by manipulating the environment. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 3545–3552 (2020)
Chen, Y., Tan, Y., Zhang, B.: Exploiting vulnerabilities of load forecasting through adversarial attacks. In: Proceedings of the Tenth ACM International Conference on Future Energy Systems, pp. 1–11 (2019)
Combita, L.F., Giraldo, J.A., Cardenas, A.A., Quijano, N.: DDDAS for attack detection and isolation of control systems. In: Blasch, E., Ravela, S., Aved, A. (eds.) Handbook of Dynamic Data Driven Applications Systems, pp. 407–422. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-95504-9_17
Darema, F.: Dynamic data driven applications systems: a new paradigm for application simulations and measurements. In: Bubak, M., van Albada, G.D., Sloot, P.M.A., Dongarra, J. (eds.) Computational Science - ICCS 2004. Lecture Notes in Computer Science, vol. 3038, pp. 662–669. Springer, Berlin (2004). https://doi.org/10.1007/978-3-540-24688-6_86
Darema, F., Blasch, E., Ravela, S., Aved, A.: Dynamic Data Driven Applications Systems: Third International Conference, DDDAS 2020, Boston, MA, USA, October 2–4, 2020, Proceedings, vol. 12312. Springer Nature, Cham (2020). https://doi.org/10.1007/978-3-030-61725-7
Dsouza, G., Hariri, S., Al-Nashif, Y., Rodriguez, G.: Resilient dynamic data driven application systems (rDDDAS). Procedia Comput. Sci. 18, 1929–1938 (2013)
Ekin, T., Cabellaro, W.N., Camacho, J.M., Naveiro, R.: Adversarial forecasting: a decision theoretic approach (2022)
Ekin, T., Damien, P., Zarnikau, J.: Estimating marginal effects of key factors that influence wholesale electricity demand and price distributions in Texas via quantile variable selection methods. J. Energy Markets 13(1), 1–29 (2020)
Ekin, T., Naveiro, R., Insua, D.R., Torres-Barrán, A.: Augmented probability simulation methods for sequential games. Eur. J. Oper. Res. (2022). https://doi.org/10.1016/j.ejor.2022.06.042
Insua, D.R., Naveiro, R., Gallego, V., Poulos, J.: Adversarial machine learning: perspectives from adversarial risk analysis. arXiv preprint: arXiv:2003.03546 (2020)
Lee, C.M., Ko, C.N.: Short-term load forecasting using lifting scheme and ARIMA models. Expert Syst. Appl. 38(5), 5902–5911 (2011)
Li, X., Miller, D.J., Xiang, Z., Kesidis, G.: A scalable mixture model based defense against data poisoning attacks on classifiers. In: Darema, F., Blasch, E., Ravela, S., Aved, A. (eds.) Dynamic Data Driven Applications Systems. Lecture Notes in Computer Science(), vol. 12312, pp. 262–273. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61725-7_31
Nguyen, H., Hansen, C.K.: Short-term electricity load forecasting with time series analysis. In: 2017 IEEE International Conference on Prognostics and Health Management (ICPHM), pp. 214–221. IEEE (2017)
Xiong, L., Sunderam, V., Fan, L., Goryczka, S., Pournajaf, L.: Privacy and security issues in DDDAS systems. In: Blasch, E.P., Darema, F., Ravela, S., Aved, A.J. (eds.) Handbook of Dynamic Data Driven Applications Systems, pp. 615–630. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-74568-4_27
Yao, L., Tunc, C., Satam, P., Hariri, S.: Resilient machine learning (rML) ensemble against adversarial machine learning attacks. In: Darema, F., Blasch, E., Ravela, S., Aved, A. (eds.) Dynamic Data Driven Applications Systems. Lecture Notes in Computer Science(), vol. 12312, pp. 274–282. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61725-7_32
Zhou, X., Canady, R., Li, Y., Koutsoukos, X., Gokhale, A.: Overcoming stealthy adversarial attacks on power grid load predictions through dynamic data repair. In: Darema, F., Blasch, E., Ravela, S., Aved, A. (eds.) Dynamic Data Driven Applications Systems. Lecture Notes in Computer Science(), vol. 12312, pp. 102–109. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61725-7_14
Zhou, X., et al.: Evaluating resilience of grid load predictions under stealthy adversarial attacks. In: 2019 Resilience Week (RWS), vol. 1, pp. 206–212. IEEE (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ekin, T., Naveiro, R., Rodriguez, J.M.C. (2024). Adversarial Forecasting Through Adversarial Risk Analysis Within a DDDAS Framework. In: Blasch, E., Darema, F., Aved, A. (eds) Dynamic Data Driven Applications Systems. DDDAS 2022. Lecture Notes in Computer Science, vol 13984. Springer, Cham. https://doi.org/10.1007/978-3-031-52670-1_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-52670-1_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-52669-5
Online ISBN: 978-3-031-52670-1
eBook Packages: Computer ScienceComputer Science (R0)