Encryption Based Covert Channel for Large Language Models

ePrint Report: Encryption Based Covert Channel for Large Language Models

Yongge Wang

Transformer neural networks have gained significant traction since their introduction, becoming pivotal across diverse domains. Particularly in large language models like Claude and ChatGPT, the transformer architecture has demonstrated remarkable efficacy. This paper provides a concise overview of transformer neural networks and delves into their security considerations, focusing on covert channel attacks and their implications for the safety of large language models. We present a covert channel utilizing …

architecture channel chatgpt claude covert covert channel domains encryption eprint report introduction language language models large networks neural networks report wang