THUYimingLi/backdoor-learning-resources

A list of backdoor learning resources

48
/ 100
Emerging

This resource helps machine learning researchers and security professionals understand and address security vulnerabilities in AI models. It compiles research papers and tools related to 'backdoor learning,' where a model behaves normally until a specific, hidden trigger activates malicious behavior. The collection categorizes various attack methods and defensive strategies against these 'neural Trojans' in AI systems, providing a comprehensive overview for anyone working with third-party models or sensitive AI applications.

1,163 stars. No commits in the last 6 months.

Use this if you are a machine learning security researcher, practitioner, or academic who needs to understand the landscape of 'backdoor' attacks and defenses in AI systems.

Not ideal if you are looking for a general introduction to machine learning or a resource focused on traditional cybersecurity threats outside of AI models.

AI security machine learning integrity neural network vulnerabilities model auditing adversarial AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

1,163

Forks

174

Language

License

MIT

Last pushed

Jul 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/THUYimingLi/backdoor-learning-resources"

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