University of Waterloo

A university in Waterloo, Ontario, Canada, whose researchers developed zkLLM, a zero-knowledge proof system for large language model inference.

The University of Waterloo is in Waterloo, Ontario, Canada; all three authors of zkLLM list it as their affiliation ¹. Their work includes:

Their CCS 2024 paper presents zkLLM, a zero-knowledge proof system for large language model inference ¹; see Zero-knowledge proofs of inference.
The authors released the zkLLM code as an artifact after the conference's artifact evaluation, archived on Zenodo ². The GitHub repository was made read-only in July 2025, and its author states that the project is no longer actively maintained ².
The authors wrote that zero-knowledge proofs of LLM training "may pose insurmountable challenges" ¹; see Zero-knowledge proofs of training constraints.

On this page

Implementations

Implementations this organization develops.

R2zkLLM
zkLLM is a GPU-accelerated zero-knowledge proof system that proves a large language model's output came from committed weights without revealing those weights.

Mechanisms and implementations whose records cite or describe this organization's work.

R2Zero-knowledge proofs of inference
A prover produces a cryptographic proof that an output came from running a committed model on a given input, without revealing the weights.

Sources this organization authored or published.

AH. Sun et al. (2024). zkLLM: Zero Knowledge Proofs for Large Language Models. 2024 ACM SIGSAC Conference on Computer and Communications Security (CCS 2024). Source recordSupports: zkLLM paper; all three authors at the University of Waterloo; view on proofs of training
BH. Sun (2024). zkllm-ccs2024: code for zkLLM: Zero Knowledge Proofs for Large Language Models. GitHub; archived on Zenodo. Source recordSupports: zkLLM code and artifact; repository archived and no longer maintained