zkLLM: Zero Knowledge Proofs for Large Language Models

TL;DR

This paper introduces zkLLM, a novel zero-knowledge proof system tailored for large language models, enabling efficient, privacy-preserving verification of LLM outputs and operations, including attention mechanisms, with practical performance on billion-parameter models.

Contribution

The paper presents the first specialized zero-knowledge proof for LLMs, including a parallelized lookup argument and a proof for attention mechanisms, significantly improving verification efficiency and privacy.

Findings

Proof generation for 13B parameter LLMs in under 15 minutes

Proof size is less than 200 kB, ensuring compactness

Achieves privacy preservation of model parameters

Abstract

The recent surge in artificial intelligence (AI), characterized by the prominence of large language models (LLMs), has ushered in fundamental transformations across the globe. However, alongside these advancements, concerns surrounding the legitimacy of LLMs have grown, posing legal challenges to their extensive applications. Compounding these concerns, the parameters of LLMs are often treated as intellectual property, restricting direct investigations. In this study, we address a fundamental challenge within the realm of AI legislation: the need to establish the authenticity of outputs generated by LLMs. To tackle this issue, we present zkLLM, which stands as the inaugural specialized zero-knowledge proof tailored for LLMs to the best of our knowledge. Addressing the persistent challenge of non-arithmetic operations in deep learning, we introduce tlookup, a parallelized lookup argument designed for non-arithmetic tensor operations in deep learning, offering a solution with no asymptotic overhead. Furthermore, leveraging the foundation of tlookup, we introduce zkAttn, a specialized zero-knowledge proof crafted for the attention mechanism, carefully balancing considerations of running time, memory usage, and accuracy. Empowered by our fully parallelized CUDA implementation, zkLLM emerges as a significant stride towards achieving efficient zero-knowledge verifiable computations over LLMs. Remarkably, for LLMs boasting 13 billion parameters, our approach enables the generation of a correctness proof for the entire inference process in under 15 minutes. The resulting proof, compactly sized at less than 200 kB, is designed to uphold the privacy of the model parameters, ensuring no inadvertent information leakage.