ICME-Lab/jolt-atlas
Fast zkVM born at a16z Crypto substantially adapted by ICME Labs (NovaNet) for verifiable machine learning. ⚡
This framework helps machine learning practitioners verify the integrity of their AI model's predictions without revealing sensitive underlying data. You provide your ONNX machine learning model, and it generates a verifiable proof of its inference, confirming that the model processed the input correctly. This is ideal for anyone deploying AI models in regulated industries or applications where trust and privacy are paramount.
Use this if you need to cryptographically prove that your machine learning model produced a specific output from an input, without exposing the input data or model details.
Not ideal if your primary concern is simply deploying or speeding up machine learning inference without the need for zero-knowledge proofs.
Stars
49
Forks
4
Language
Rust
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ICME-Lab/jolt-atlas"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
socathie/circomlib-ml
Circom Circuits Library for Machine Learning
mithril-security/blindai
Confidential AI deployment with secure enclaves :lock:
gizatechxyz/LuminAIR
A zkML framework for ensuring the integrity of computational graphs using Circle STARK proofs
SpeyTech/certifiable-inference
Deterministic, bit-perfect AI inference for safety-critical systems
guruvamsi-policharla/zkpot
A prototype implementation of zero-knowledge proofs of training introduced in eprint:2023/1345