# opp/ai: Optimistic Privacy-Preserving AI on Blockchain

arXiv: https://arxiv.org/abs/2402.15006 · HTML: https://mlsanity.com/paper/2402.15006/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 22 Feb 2024.

## Builds on (most cited first, 9 of 9)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Distributed Deep Neural Networks over the Cloud, the Edge and End Devices](https://mlsanity.com/paper/1709.01921/) (2017)
- [Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms](https://mlsanity.com/paper/1802.03835/) (2018)
- [opML: Optimistic Machine Learning on Blockchain](https://mlsanity.com/paper/2401.17555/) (2024)
- [Agatha: Smart Contract for DNN Computation](https://mlsanity.com/paper/2105.04919/) (2021)
- [Dispute-free Scalable Open Vote Network using zk-SNARKs](https://mlsanity.com/paper/2203.03363/) (2022)

## Built on by (most cited first, 1 of 1)

- [Hawkeye: Reproducing GPU-Level Non-Determinism](https://mlsanity.com/paper/2603.20421/) (2026)

## Abstract (arXiv)

The convergence of Artificial Intelligence (AI) and blockchain technology is reshaping the digital world, offering decentralized, secure, and efficient AI services on blockchain platforms. Despite the promise, the high computational demands of AI on blockchain raise significant privacy and efficiency concerns. The Optimistic Privacy-Preserving AI (opp/ai) framework is introduced as a pioneering solution to these issues, striking a balance between privacy protection and computational efficiency. The framework integrates Zero-Knowledge Machine Learning (zkML) for privacy with Optimistic Machine Learning (opML) for efficiency, creating a hybrid model tailored for blockchain AI services. This study presents the opp/ai framework, delves into the privacy features of zkML, and assesses the framework's performance and adaptability across different scenarios.