Taking Over the Stock Market: Adversarial Perturbations Against Algorithmic Traders

TL;DR

This paper demonstrates that adversarial perturbations can manipulate algorithmic trading systems in real-time, exposing vulnerabilities in machine learning models used for stock market prediction and trading.

Contribution

It introduces a universal, model-agnostic adversarial attack on trading algorithms and evaluates its effectiveness on real market data, highlighting security risks.

Findings

Adversarial perturbations can fool trading algorithms on unseen data.

The attack is effective in both white-box and black-box settings.

Mitigation methods have limitations in the trading context.

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 perturbation that is agnostic to the target model and time of use, which, when added to the input stream, remains imperceptible. 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 an alert to the finance community about the threats in this area and promote further research on the risks associated with using automated learning models in the trading domain.