Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning

TL;DR

This paper introduces a novel backdoor attack method called FinanceLLMsBackRL targeting reinforcement learning-based financial models, emphasizing data poisoning and detection techniques to assess vulnerabilities in AI systems used in finance and other fields.

Contribution

It presents a new backdoor attack approach specific to reinforcement learning in finance, with detection strategies based on dynamic systems and statistical analysis.

Findings

The attack can effectively poison data without triggers.

Detection methods can identify anomalies in data distribution.

The approach highlights vulnerabilities in AI models used in finance.

Abstract

With the rapid development of generative artificial intelligence, particularly large language models a number of sub-fields of deep learning have made significant progress and are now very useful in everyday applications. For example,financial institutions simulate a wide range of scenarios for various models created by their research teams using reinforcement learning, both before production and after regular operations. In this work, we propose a backdoor attack that focuses solely on data poisoning and a method of detection by dynamic systems and statistical analysis of the distribution of data. This particular backdoor attack is classified as an attack without prior consideration or trigger, and we name it FinanceLLMsBackRL. Our aim is to examine the potential effects of large language models that use reinforcement learning systems for text production or speech recognition, finance, physics, or the ecosystem of contemporary artificial intelligence models.