Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning
This addresses security vulnerabilities in AI models used in finance, but it appears incremental as it builds on existing backdoor attack concepts without specifying novel breakthroughs.
The paper tackles the problem of backdoor attacks in AI systems by proposing a data poisoning method named FinanceLLMsBackRL, which targets reinforcement learning models in financial applications, and it introduces a detection approach using dynamic systems and statistical analysis.
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.