Prizes Available 
$0 Total Prizes: $0
Prizes Awarded: $0
Trending Challenges 
Details |
---|
![]() In-progress ![]() Use image inputs to jailbreak leading vision-enabled AI models. Visual prompt injections, chem/bio/cyber weaponization, privacy violations, and more. Open Challenge View Leaderboard |

Details |
---|
![]() In-progress ![]() Push the limits of direct and indirect attacks on AI agents. Sponsored by: AI Security Institute OpenAI Anthropic Google DeepMind Open Challenge View Leaderboard |

Play within our long-running challenges and break AI models in your free time
View Leaderboard

Connect with AI enthusiasts and experts from around the world
Join Discord Server
Substantial Prizes 
Win recognition and rewards for your innovative jailbreaks
View Prizes

Featured Challenges 
Compete in these AI security challenges to win prizes and improve your skills.
Details |
---|
In-progress ![]() Use image inputs to jailbreak leading vision-enabled AI models. Visual prompt injections, chem/bio/cyber weaponization, privacy violations, and more. Open Challenge View Leaderboard |
In-progress ![]() Push the limits of direct and indirect attacks on AI agents. Sponsored by: AI Security Institute OpenAI Anthropic Google DeepMind Open Challenge View Leaderboard |
Completed ![]() Jailbreak the helpful AI assistants to aid in harmful tasks across six areas. Open Challenge View Leaderboard |
Completed ![]() Elicit harmful outputs from LLMs through long-context interactions across multiple messages. Open Challenge View Leaderboard |
Completed ![]() Jailbreak multimodal LLMs through a combination of visual and text inputs. Open Challenge View Leaderboard |
Completed ![]() Find unique ways to return functional code that completes harmful tasks such as opening circuit breakers to cause a system-wide blackout. Open Challenge View Leaderboard |
Completed ![]() Attack OpenAI's o1 model to try and reveal its internal chain of thought (CoT) that's used for its complex reasoning. Sponsored by: OpenAI Open Challenge View Leaderboard |
In-progress ![]() Attempt to break various large language models (LLMs) using a singular chat message. Open Challenge View Leaderboard |

Top Winners
Rank | Participant | Prize |
---|---|---|
![]() |
Solomon Zoe | $10,165 |
![]() |
Clovis Mint | $7,072 |
![]() |
Scrattlebeard | $5,650 |