AI/LLM Red Team Handbook and Field Manual

I've published a handbook for penetration testing AI systems and LLMs: https://cph-sec.gitbook.io/ai-llm-red-team-handbook-and-field-manual

Contents:

• AI/LLM reconnaissance methodologies

• Prompt injection attack vectors

• Data exfiltration techniques

• Jailbreak strategies

• Automated testing tools and frameworks

• Defense evasion methods

• Practical attack scenarios

Target audience: pentesters, red teamers, and security researchers assessing AI-integrated applications, chatbots, and LLM implementations.

Open to feedback and contributions from the community.