mithril-security/blindai
Confidential AI deployment with secure enclaves :lock:
BlindAI helps organizations and individuals use AI models without exposing their sensitive data to the model provider. You feed your confidential data, like patient audio or medical images, into an AI model, and it outputs the analysis, such as a transcription or diagnosis probability, while keeping your original data completely private. This is for any professional or organization that needs to leverage AI but has strict privacy requirements for their input data.
512 stars. No commits in the last 6 months.
Use this if you need to perform AI analysis on highly sensitive or confidential data and cannot risk exposing that data to the AI model host or provider.
Not ideal if your data is not sensitive, or if you require an actively maintained solution for processing confidential data.
Stars
512
Forks
35
Language
Rust
License
Apache-2.0
Category
Last pushed
Mar 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mithril-security/blindai"
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
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
guruvamsi-policharla/zkpot
A prototype implementation of zero-knowledge proofs of training introduced in eprint:2023/1345