# ZKTorch: Compiling ML Inference to Zero-Knowledge Proofs via Parallel Proof Accumulation

arXiv: https://arxiv.org/abs/2507.07031 · HTML: https://mlsanity.com/paper/2507.07031/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 41 references that are in the map.
- First posted on arXiv 9 Jul 2025.

## Builds on (most cited first, 6 of 6)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [MLPerf Inference Benchmark](https://mlsanity.com/paper/1911.02549/) (2019)
- [pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testing](https://mlsanity.com/paper/2201.09186/) (2022)
- [Trustless Audits without Revealing Data or Models](https://mlsanity.com/paper/2404.04500/) (2024)
- [Why and How zk-SNARK Works](https://mlsanity.com/paper/1906.07221/) (2019)

## Built on by (most cited first, 3 of 3)

- [SPRINT: Robust Model Attribution of Generated Images via Secret Pixel Reconstruction](https://mlsanity.com/paper/2508.05691/) (2025)
- [JSTprove: Pioneering Verifiable AI for a Trustless Future](https://mlsanity.com/paper/2510.21024/) (2025)
- [ZK-SR117: A Chunked Zero-Knowledge Attestation Design for Aggregated Fair-Lending Metrics, with a Control Mapping toward Full SR 11-7 Coverage](https://mlsanity.com/paper/2608.02664/) (2026)

## Abstract (arXiv)

As AI models become ubiquitous in our daily lives, there has been an increasing demand for transparency in ML services. However, the model owner does not want to reveal the weights, as they are considered trade secrets. To solve this problem, researchers have turned to zero-knowledge proofs of ML model inference. These proofs convince the user that the ML model output is correct, without revealing the weights of the model to the user. Past work on these provers can be placed into two categories. The first method compiles the ML model into a low-level circuit, and proves the circuit using a ZK-SNARK. The second method uses custom cryptographic protocols designed only for a specific class of models. Unfortunately, the first method is highly inefficient, making it impractical for the large models used today, and the second method does not generalize well, making it difficult to update in the rapidly changing field of machine learning. To solve this, we propose ZKTorch, an open source end-to-end proving system that compiles ML models into base cryptographic operations called basic blocks, each proved using specialized protocols. ZKTorch is built on top of a novel parallel extension to the Mira accumulation scheme, enabling succinct proofs with minimal accumulation overhead. These contributions allow ZKTorch to achieve at least a 3× reduction in the proof size compared to specialized protocols and up to a 6× speedup in proving time over a general-purpose ZKML framework.