Zhaohui Geoffrey Wang

NANOZK introduces a novel, highly efficient zero-knowledge proof system that allows users to cryptographically verify that the output of a large language model (LLM) was generated by a specific, claimed model, preventing service provider fraud.

The paper proposes a novel '3+1' heterogeneous multi-agent architecture using cloud LLMs and a local verifier to achieve high-accuracy, cost-effective code vulnerability detection, significantly outperforming single-expert and traditional static analysis methods.