Ryanditko/federated-learning-at-cybersecurity

Este projeto de iniciação científica tem como objetivo investigar e desenvolver soluções baseadas em Aprendizado Federado, um paradigma de inteligência artificial descentralizada que permite o treinamento colaborativo de modelos de machine learning sem a necessidade de centralizar dados sensíveis.

22
/ 100
Experimental

When multiple organizations collaborate to build a machine learning model using their private data, this project helps detect and neutralize malicious attempts to corrupt the shared model. It takes model updates from contributing parties and identifies harmful contributions, outputting a more secure, robust global model. This is for cybersecurity professionals, data scientists, or IT managers responsible for securing AI systems that learn from distributed, sensitive data.

Use this if you are building or managing a federated learning system and need to protect it from 'poisoning attacks' that could degrade its performance or introduce vulnerabilities.

Not ideal if your machine learning models are trained on centralized, trusted data sources, as the core problem this solves (distributed data privacy and security) would not apply.

cybersecurity federated-learning data-privacy threat-detection distributed-ai-security
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 7 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Jupyter Notebook

License

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Ryanditko/federated-learning-at-cybersecurity"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.