Abstract
In recent years, machine learning has become prevalent in numerous tasks, including algorithmic trading. Stock market traders utilize machine learning models to predict the market’s behavior and execute an investment strategy accordingly. However, machine learning models have been shown to be susceptible to input manipulations called adversarial examples. Despite this risk, the trading domain remains largely unexplored in the context of adversarial learning. In this study, we present a realistic scenario in which an attacker influences algorithmic trading systems by using adversarial learning techniques to manipulate the input data stream in real time. The attacker creates a universal adversarial perturbation that is agnostic to the target model and time of use, which remains imperceptible when added to the input stream. We evaluate our attack on a real-world market data stream and target three different trading algorithms. We show that when added to the input stream, our perturbation can fool the trading algorithms at future unseen data points, in both white-box and black-box settings. Finally, we present various mitigation methods and discuss their limitations, which stem from the algorithmic trading domain. We believe that these findings should serve as a warning to the finance community regarding the threats in this area and promote further research on the risks associated with using automated learning models in the trading domain.
E. Nehemya and Y. Mathov—Both authors contributed equally.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arévalo, A., Niño, J., Hernández, G., Sandoval, J.: High-frequency trading strategy based on deep neural networks. In: Huang, D.-S., Han, K., Hussain, A. (eds.) ICIC 2016. LNCS (LNAI), vol. 9773, pp. 424–436. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-42297-8_40
Arnoldi, J.: Computer algorithms, market manipulation and the institutionalization of high frequency trading. Theory Cult. Soc. 33(1), 29–52 (2016)
Athalye, A., Carlini, N., Wagner, D.: Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples. In: International Conference on Machine Learning, pp. 274–283. PMLR (2018)
Bianchi, D., Tosun, O.K.: Cyber attacks and stock market activity. SSRN (2019)
Bigiotti, A., Navarra, A.: Optimizing automated trading systems. In: Antipova, T., Rocha, A. (eds.) DSIC18 2018. AISC, vol. 850, pp. 254–261. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-02351-5_30
Chen, G., Chen, Y., Fushimi, T.: Application of deep learning to algorithmic trading. Stanford. https://stanford.io/3dllsMC. Accessed June 2021
Chong, E., Han, C., Park, F.C.: Deep learning networks for stock market analysis and prediction: methodology, data representations, and case studies. Expert Syst. Appl. 83, 187–205 (2017)
Coutts, J.A., Cheung, K.C.: Trading rules and stock returns: some preliminary short run evidence from the Hang Seng 1985–1997. Appl. Financ. Econ. 10(6), 579–586 (2000)
Domm, P.: False rumor of explosion at white house causes stocks to briefly plunge. CNBC (2013). https://cnb.cx/35SVKKU. Accessed June 2021
Fisher, M.: Syrian hackers claim AP hack that tipped stock market by \$136 billion. Is it terrorism? Washington Post 23 (2013)
Giacomel, F., Galante, R., Pereira, A.: An algorithmic trading agent based on a neural network ensemble: a case of study in North American and Brazilian stock markets. In: 2015 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), vol. 2, pp. 230–233. IEEE (2015)
Goldblum, M., Schwarzschild, A., Cohen, N., Balch, T., Patel, A.B., Goldstein, T.: Adversarial attacks on machine learning systems for high-frequency trading. arXiv:2002.09565 (2020)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv:1412.6572 (2014)
Gunning, D.: Explainable artificial intelligence (XAI). Defense Advanced Research Projects Agency (DARPA), nd Web 2, 2 (2017)
Kumar, G., Jain, S., Singh, U.P.: Stock market forecasting using computational intelligence: a survey. Arch. Comput. Methods Eng. 28(3), 1069–1101 (2020). https://doi.org/10.1007/s11831-020-09413-5
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv:1706.06083 (2017)
Matt, E.: February was an insane month for the stock market. CNN (2018). https://cnn.it/3j8Q7Ah. Accessed June 2021
Mitchell, C.: Erroneous trade. Investopedia (2021). https://bit.ly/2SxaU5C. Accessed June 2021
Moosavi-Dezfooli, S.M., Fawzi, A., Fawzi, O., Frossard, P.: Universal adversarial perturbations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1765–1773 (2017)
Nakashima, E.: Hack, pump and dump. The Washington Post (2007). https://wapo.st/3vSsIWs. Accessed June 2021
Neyret, A.: Stock market cybercrime. Autorité des Marchés Financiers (2020). https://bit.ly/3xPE0wg. Accessed June 2021
Nickdl: S&P 500 intraday data. Kaggle (2018). https://bit.ly/3gRJgJV. Accessed June 2021
Pang, X., Zhou, Y., Wang, P., Lin, W., Chang, V.: An innovative neural network approach for stock market prediction. J. Supercomput. 76(3), 2098–2118 (2018). https://doi.org/10.1007/s11227-017-2228-y
Rooney, K., Khorram, Y.: Hackers look to buy brokerage log-ins on the dark web with Robinhood fetching highest prices. CNBC (2020). https://cnb.cx/3zX9an1. Accessed June 2021
Smith, T.: Broker. Investopedia (2020). https://bit.ly/2SVpWCC. Accessed June 2021
Stacey, B.C., Bar-Yam, Y.: The stock market has grown unstable since February 2018. arXiv:1806.00529 (2018)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv:1312.6199 (2013)
Treleaven, P., Galas, M., Lalchand, V.: Algorithmic trading review. Commun. ACM 56(11), 76–85 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Nehemya, E., Mathov, Y., Shabtai, A., Elovici, Y. (2021). Taking over the Stock Market: Adversarial Perturbations Against Algorithmic Traders. In: Dong, Y., Kourtellis, N., Hammer, B., Lozano, J.A. (eds) Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track. ECML PKDD 2021. Lecture Notes in Computer Science(), vol 12978. Springer, Cham. https://doi.org/10.1007/978-3-030-86514-6_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-86514-6_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86513-9
Online ISBN: 978-3-030-86514-6
eBook Packages: Computer ScienceComputer Science (R0)