mirror of
https://github.com/privacy-scaling-explorations/pse.dev.git
synced 2026-01-14 16:48:02 -05:00
19 lines
1.2 KiB
Markdown
19 lines
1.2 KiB
Markdown
---
|
|
id: "zkml"
|
|
name: "ZKML"
|
|
image: "zkml.webp"
|
|
section: "pse"
|
|
projectStatus: "inactive"
|
|
category: "research"
|
|
tldr: "ZKML (Zero-Knowledge Machine Learning) leverages zero-knowledge proofs for privacy-preserving machine learning, enabling model and data privacy with transparent verification."
|
|
tags:
|
|
keywords: ["Anonymity/privacy", "Scaling"]
|
|
themes: ["research"]
|
|
types: ["Proof of concept", "Infrastructure/protocol"]
|
|
builtWith: ["circom", "halo2", "nova"]
|
|
links:
|
|
github: "https://github.com/socathie/circomlib-ml"
|
|
---
|
|
|
|
ZKML is a solution that combines the power of zero-knowledge proofs (ZKPs) and machine learning to address the privacy concerns in traditional machine learning. It provides a platform for machine learning developers to convert their TensorFlow Keras models into ZK-compatible versions, ensuring model privacy, data privacy, and transparent verification. ZKML can be used to verify if a specific machine learning model was used to generate a particular piece of content, without revealing the input or the model used. It has potential use cases in on-chain biometric authentication, private data marketplace, proprietary ML model sharing, and AIGC NFTs.
|