asif-hanif/baple

[MICCAI 2024] Official code repository of paper titled "BAPLe: Backdoor Attacks on Medical Foundation Models using Prompt Learning" accepted in MICCAI 2024 conference.

24
/ 100
Experimental

This project helps medical professionals, researchers, and developers assess the security of medical AI models. It introduces a method to embed a 'backdoor' into medical foundation models during the prompt learning phase. The input is a medical image, and the output is a classification result that can be manipulated under specific, imperceptible trigger conditions. It is designed for those involved in developing, deploying, or auditing AI systems in healthcare.

No commits in the last 6 months.

Use this if you are a medical AI researcher, developer, or auditor concerned with evaluating the robustness and security of medical foundation models against stealthy adversarial attacks.

Not ideal if you are looking to secure a deployed medical AI system without understanding the underlying vulnerabilities, or if you need a general-purpose cybersecurity tool outside of medical imaging AI.

medical-AI-security healthcare-AI-auditing medical-image-analysis AI-vulnerability-assessment foundation-model-security
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

56

Forks

Language

Python

License

MIT

Last pushed

Oct 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/asif-hanif/baple"

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