emaballarin/CARSO

👀🛡️ Code for the paper “Blending adversarial training and representation-conditional purification via aggregation improves adversarial robustness” by Emanuele Ballarin, Alessio Ansuini and Luca Bortolussi (2025)

35
/ 100
Emerging

This project helps researchers and practitioners evaluate and improve the security of their AI models against deliberate attacks. It takes an existing image classification model and training data, and then applies advanced techniques to make the model more resilient, providing a more robust and trustworthy model as an output. This is for anyone building or deploying AI systems where reliability and security against adversarial examples are critical.

No commits in the last 6 months.

Use this if you need to make your image classification models more robust against adversarial attacks that try to trick them.

Not ideal if you are working with non-image data or if your primary concern is model accuracy without considering adversarial threats.

AI security model robustness image classification adversarial machine learning deep learning defense
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

8

Forks

2

Language

Python

License

MIT

Last pushed

Sep 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/emaballarin/CARSO"

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