Contents#

• OWASP Top 10 for Large Language Model Applications
• Prompt Injection Articles
• Prompt Injection Videos
• Prompt Injection CTF
• LLM Hacker Handbook
• Videos
• AI Attack Surface Map
• Research Papers

OWASP Top 10 for Large Language Model Applications#

• https://owasp.org/www-project-top-10-for-large-language-model-applications/

Prompt Injection Articles#

• https://josephthacker.com/ai/2023/04/19/prompt-injection-and-mitigations.html
• https://josephthacker.com/ai/2023/08/25/prompt-injection-primer.html
• https://research.nccgroup.com/2022/12/05/exploring-prompt-injection-attacks/
• https://www.lakera.ai/insights/what-is-prompt-injection

Prompt Injection Videos#

• Attacking LLM - Prompt Injection
• Accidental LLM Backdoor - Prompt Tricks
• Defending LLM - Prompt Injection
• Prompt Injection 101 - Understanding Security Risks in LLM

Prompt Injection CTF#

• GPT Prompt Attack
• Double Speak Chat

LLM Hacker Handbook#

• https://doublespeak.chat/#/handbook

Videos#

• AI Hacking 🔥 OWASP Top 10 Vulnerabilities in LLM Applications
• Fredrik Heiding - Devising and Detecting Phishing: Large Language Models vs. Smaller Human Models
• Daniel Miessler and Rez0: Hacking with AI (Ep. 24)
• AI and hacking - opportunities and threats - Joseph “rez0” Thacker

AI Attack Surface Map#

• The AI Attack Surface Map v1.0

Research Papers#

• Prompt Injection attack against LLM-integrated Applications
• Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
• Universal and Transferable Adversarial Attacks on Aligned Language Models