Skip to content
Inside the AI Red Teaming CTF: What 200+ Players Taught Us About Breaking and Defending LLMs
hackerone.com | blog | #ai-security | #red-teaming | #ctf | #prompt-injection | #jailbreak | #llm-security | #hackerone | #ai-red-teaming | #hack-the-box | #owasp-llm-top-10
Summary
In a 10-day AI red teaming CTF with 217 active players, output manipulation succeeded ~82.5% and data extraction ~74.6%; layered defenses cut completion to ~34% on the hardest multi-step challenge.
- Published
- Collected