Frameworks, blogs and articles
- Offensive ML playbook
- Embrace the Red – blog about hacking AI
- Microsoft: Planning red teaming of LLMs
- OWASP: GenAI red teaming guide
- Google: AI assisted fuzzing
- Lakera: Fuzzing AI
- HackerNews article on PyRIT
- Bad Likert Judge – multiturn jailbreak method for LLMs
- Emoji attack
Open source tools
- Microsoft: red teaming tool for GenAI
- AI goat – deliberately vulnerable AI infrastructure
- Promptmap – tool for testing prompt injection vulnerabilities
- LLM powered fuzzing
- Fuzzing LLMs
- Hacking buddy LLM
- LLM hacking database
AI cybersecurity and risk management
- OWASP LLM top 10
- OWASP LLM application top 10 – 2025
- OWASP Machine learning top 10
- OWASP Agentic AI threats and mitigations
- OWASP LLM prompt hacking guide
- NIST AI 100-2 E2023 Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations
- MITRE ALTAS
- Google SAIF (AI security) framework
- NIST AI RMF Playbook