vt-asaplab/ezDPS
ezDPS: An Efficient and Zero-Knowledge Machine Learning Inference Pipeline
ezDPS is a research project providing an efficient and privacy-preserving way to run machine learning models, specifically for tasks like image classification or time-series analysis. It takes your raw data and a trained machine learning model, then outputs classification results while generating a verifiable 'proof' that the model was run correctly without revealing the underlying data or model specifics. This is primarily for researchers and privacy-focused engineers developing secure machine learning systems.
No commits in the last 6 months.
Use this if you are a researcher or engineer looking to experiment with or implement zero-knowledge proofs for secure machine learning inference, where data privacy and result verification are critical.
Not ideal if you are a data scientist or practitioner simply looking to train and deploy standard machine learning models without a specific focus on zero-knowledge proofs or advanced cryptographic privacy guarantees.
Stars
21
Forks
—
Language
Rust
License
—
Category
Last pushed
Jul 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/vt-asaplab/ezDPS"
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