CipherMind: The Longest Codebook in the World

TL;DR

CipherMind introduces a novel encryption method leveraging intermediate results from large language models' inference processes, enabling secure data transmission by exploiting the semantic properties of model parameters.

Contribution

It proposes a new communication encryption paradigm using large models' inference outputs, expanding the application scope of language models beyond traditional tasks.

Findings

Demonstrates feasibility of using model inference as encryption

Applicable to various large models and scenarios

Provides a theoretical foundation for model-based encryption

Abstract

In recent years, the widespread application of large language models has inspired us to consider using inference for communication encryption. We therefore propose CipherMind, which utilizes intermediate results from deterministic fine-tuning of large model inferences as transmission content. The semantic parameters of large models exhibit characteristics like opaque underlying implementations and weak interpretability, thus enabling their use as an encryption method for data transmission. This communication paradigm can be applied in scenarios like intra-gateway transmission, and theoretically, it can be implemented using any large model as its foundation.