Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915252850917376 |
|---|---|
| author | Mengara, Orson |
| author_facet | Mengara, Orson |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_17908 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning Mengara, Orson Machine Learning Computational Engineering, Finance, and Science Computational Physics Physics and Society 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. |
| title | Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning |
| topic | Machine Learning Computational Engineering, Finance, and Science Computational Physics Physics and Society |
| url | https://arxiv.org/abs/2412.17908 |