The Nillion community wants to see more Blind AI Apps. Create and launch a Blind AI application on the Nillion Testnet and provide a live link so anyone can try it. Your Blind AI App should use at least 1 Nada program with the Nada AI library to provide predictions while ensuring data privacy.
Bounty Requirements
Create a new Bind AI App using the following workflow:
Pick an Interesting Data Set:
Choose a dataset that is suitable for your AI project. The dataset should be relevant and provide meaningful insights.
Train a Plaintext Model:
Use your preferred AI tools to train a model on the chosen dataset. Check out examples and Google Colab links in nada-ai examples. Here are the available models:
Multilayer Perceptron: Available layers include Linear, Conv2d, AvgPooling2d, DotProductSimilarity, ReLU, Flatten
Linear Regression Model: Linear model
Logistic Regression Model: Linear model implementation with cleartext sigmoid and potential multiclass classification
Prophet: Time series forecasting model
Write at Least One Nada Program that utilizes the nada-ai library
Ensure that your program integrates the trained model and is capable of making predictions.
Store your AI Program on the Nillion Testnet
Build a Blind App:
Build a blind app that uses the compiled Nada program to obtain live, privacy-preserving predictions from your model.
Ensure the app securely computes predictions without revealing sensitive data.
Host this web app demo and provide a live link so we can try it
How to Submit
Review the Terms and Conditions for Nillion Builder Bounties here.
Bounty Objective
The Nillion community wants to see more Blind AI Apps. Create and launch a Blind AI application on the Nillion Testnet and provide a live link so anyone can try it. Your Blind AI App should use at least 1 Nada program with the Nada AI library to provide predictions while ensuring data privacy.
Bounty Requirements
Create a new Bind AI App using the following workflow:
Pick an Interesting Data Set:
Choose a dataset that is suitable for your AI project. The dataset should be relevant and provide meaningful insights.
Train a Plaintext Model:
Use your preferred AI tools to train a model on the chosen dataset. Check out examples and Google Colab links in nada-ai examples. Here are the available models:
Write at Least One Nada Program that utilizes the nada-ai library
Ensure that your program integrates the trained model and is capable of making predictions.
Store your AI Program on the Nillion Testnet
Build a Blind App:
Build a blind app that uses the compiled Nada program to obtain live, privacy-preserving predictions from your model.
Ensure the app securely computes predictions without revealing sensitive data.
Host this web app demo and provide a live link so we can try it
How to Submit
Review the Terms and Conditions for Nillion Builder Bounties here.
Open source your repo and submit your bounty by creating a new discussion in Nillion’s “Show and Tell” Github Discussions Forum. For project type, choose “Builder Bounty Submission”