vt-asaplab/vPIN
Privacy-Preserving Verifiable Neural Network Inference Service
This project offers a prototype for creating a privacy-preserving and verifiable neural network inference service. It takes trained neural network models and new input data, producing a verified inference result without revealing the input data or the model's internal workings. This is for developers, researchers, and security professionals who need to experiment with secure machine learning solutions.
No commits in the last 6 months.
Use this if you are a researcher or developer exploring how to provide neural network inference where both the data privacy of the user and the integrity of the model's output need to be cryptographically guaranteed.
Not ideal if you need a production-ready system for deploying secure AI services, as this is a proof-of-concept prototype for research and experimentation.
Stars
16
Forks
—
Language
Rust
License
—
Category
Last pushed
Sep 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/vt-asaplab/vPIN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ICME-Lab/jolt-atlas
Fast zkVM born at a16z Crypto substantially adapted by ICME Labs (NovaNet) for verifiable...
socathie/circomlib-ml
Circom Circuits Library for Machine Learning
mithril-security/blindai
Confidential AI deployment with secure enclaves :lock:
SpeyTech/certifiable-inference
Deterministic, bit-perfect AI inference for safety-critical systems
gizatechxyz/LuminAIR
A zkML framework for ensuring the integrity of computational graphs using Circle STARK proofs