ctf-ai-ml

What problem does it solve?

CTF participants need practical techniques to assess and exploit AI/ML systems in controlled scenarios.

Core Features & Use Cases

• Technique catalog: adversarial ML, model extraction, data poisoning, membership inference, encoder collisions, LoRA exploitation, and LLM attacks with practical exercises.
• Hands-on labs: guided payloads and references to model attacks papers to reproduce results in safe test environments.
• Use Case: In a CTF, you can map an ML target's vulnerabilities and design staged exploits to retrieve flags or demonstrate weaknesses.

Quick Start

Run a practice AI/ML attack against a target model using the provided examples to observe defense gaps in a safe, controlled environment.