zihao-ai/Awesome-Backdoor-in-Deep-Learning

A curated list of papers & resources on backdoor attacks and defenses in deep learning.

37
/ 100
Emerging

This resource helps machine learning engineers and researchers understand and mitigate security risks in deep learning models. It provides a comprehensive collection of papers and resources on 'backdoor attacks'—malicious hidden functions in models—and 'backdoor defenses' to protect against them. You can use this to research various attack methods on different model types and find corresponding defense strategies.

237 stars. No commits in the last 6 months.

Use this if you are a machine learning security practitioner, researcher, or engineer focused on securing deep learning models against malicious tampering or hidden vulnerabilities.

Not ideal if you are looking for ready-to-use software tools or libraries for immediate implementation of attacks or defenses, as this is primarily a curated list of academic papers.

AI security deep learning security model robustness adversarial machine learning federated learning security
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

237

Forks

13

Language

Python

License

GPL-3.0

Last pushed

Mar 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zihao-ai/Awesome-Backdoor-in-Deep-Learning"

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