domains / families / security / ctf-ai-ml

ctf-ai-ml

separate

Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, training data poisoning, fine-tuning manipulation, neural network analysis, LoRA adapter exploitation, LLM jailbreaking, or solving AI-related puzzles.

When to use

• attacking ML models
• crafting adversarial examples
• performing model extraction
• prompt injection
• membership inference
• training data poisoning
• fine-tuning manipulation
• neural network analysis

When not to use

• pure math, lattice reduction, or number theory with no ML component
• reverse engineering a compiled ML model binary
• game or puzzle that merely uses ML as a wrapper

Skill page

Source