Trading Devil Final: Backdoor attack via Stock market and Bayesian Optimization
This addresses security risks for users of generative AI models, particularly in speech recognition systems, but appears incremental as it builds on existing backdoor attack concepts.
The paper tackles the problem of verifying what happens when large language models (LLMs) learn by developing MarketBackFinal 2.0, a backdoor attack based on acoustic data poisoning and stock market models, to demonstrate vulnerabilities in speech-based transformers that rely on LLMs.
Since the advent of generative artificial intelligence, every company and researcher has been rushing to develop their own generative models, whether commercial or not. Given the large number of users of these powerful new tools, there is currently no intrinsically verifiable way to explain from the ground up what happens when LLMs (large language models) learn. For example, those based on automatic speech recognition systems, which have to rely on huge and astronomical amounts of data collected from all over the web to produce fast and efficient results, In this article, we develop a backdoor attack called MarketBackFinal 2.0, based on acoustic data poisoning, MarketBackFinal 2.0 is mainly based on modern stock market models. In order to show the possible vulnerabilities of speech-based transformers that may rely on LLMs.