# Trust the Process: Zero-Knowledge Machine Learning to Enhance Trust in Generative AI Interactions

arXiv: https://arxiv.org/abs/2402.06414 · HTML: https://mlsanity.com/paper/2402.06414/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 9 Feb 2024.

## Builds on (most cited first, 8 of 8)

- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Fair Resource Allocation in Federated Learning](https://mlsanity.com/paper/1905.10497/) (2019)
- [Distributionally Robust Federated Averaging](https://mlsanity.com/paper/2102.12660/) (2021)
- [Enforcing fairness in private federated learning via the modified method of differential multipliers](https://mlsanity.com/paper/2109.08604/) (2021)
- [Training Fair Models in Federated Learning without Data Privacy Infringement](https://mlsanity.com/paper/2109.05662/) (2021)
- [Why and How zk-SNARK Works](https://mlsanity.com/paper/1906.07221/) (2019)

## Built on by (most cited first, 6 of 6)

- [A Survey of Zero-Knowledge Proof Based Verifiable Machine Learning](https://mlsanity.com/paper/2502.18535/) (2025)
- [Trust, but verify](https://mlsanity.com/paper/2504.13443/) (2025)
- [Hawkeye: Reproducing GPU-Level Non-Determinism](https://mlsanity.com/paper/2603.20421/) (2026)
- [Optimizing Privacy-Preserving Primitives to Support LLM-Scale Applications](https://mlsanity.com/paper/2509.25072/) (2025)
- [Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign](https://mlsanity.com/paper/2502.02068/) (2025)
- [On-Chain Decentralized Learning and Cost-Effective Inference for DeFi Attack Mitigation](https://mlsanity.com/paper/2510.16024/) (2025)

## Abstract (arXiv)

Generative AI, exemplified by models like transformers, has opened up new possibilities in various domains but also raised concerns about fairness, transparency and reliability, especially in fields like medicine and law. This paper emphasizes the urgency of ensuring fairness and quality in these domains through generative AI. It explores using cryptographic techniques, particularly Zero-Knowledge Proofs (ZKPs), to address concerns regarding performance fairness and accuracy while protecting model privacy. Applying ZKPs to Machine Learning models, known as ZKML (Zero-Knowledge Machine Learning), enables independent validation of AI-generated content without revealing sensitive model information, promoting transparency and trust. ZKML enhances AI fairness by providing cryptographic audit trails for model predictions and ensuring uniform performance across users. We introduce snarkGPT, a practical ZKML implementation for transformers, to empower users to verify output accuracy and quality while preserving model privacy. We present a series of empirical results studying snarkGPT's scalability and performance to assess the feasibility and challenges of adopting a ZKML-powered approach to capture quality and performance fairness problems in generative AI models.