Skip to content

Latest commit

 

History

History
executable file
·
93 lines (51 loc) · 3.79 KB

readme.md

File metadata and controls

executable file
·
93 lines (51 loc) · 3.79 KB

What is JailbreakMe? 🚀

jailbreakme.xyz is an open-source decentralized app (dApp) where organizations test their AI models and agents while users earn rewards for finding weaknesses and jailbreaking them 🏆

image1.jpg

What is an AI Prompt Injection? 💉

Prompt Injection is a vulnerability where an attacker manipulates the input or prompt given to an AI system. This can occur:

  • By directly controlling the input.
  • By using data from other external sources.

Our Vision

We aim to create a decentralized platform where companies can:

  • Test their AI models and agents in a distributed environment.
  • Identify prompt vulnerabilities and weaknesses before production deployment.

🏁 How It Works

1. Participate:

1.1 Choose an agent:

Screenshot 2025-02-01 at 20.28.00.png

1.2 Break the LLM Restrictions 🤖

Screenshot 2025-02-01 at 20.31.36.png

1.3 Win the Prize Pool 🏆

Screenshot 2025-02-01 at 20.32.00.png

How is the Winner Picked? 🤔

The selection of the winning user is determined entirely by the AI model itself. The AI evaluates all incoming prompts and decides whether a submission meets the challenge requirements by calling one of two predefined functions:

  1. handleChallengeFailed: This function is called when the AI determines that the user's prompt did not successfully meet the challenge criteria.
  2. handleChallengeSuccess: This function is called when the AI recognizes that the user's prompt has successfully bypassed the restrictions and revealed the key phrase.

When the handleChallengeSuccess function is triggered, the prize pool is automatically awarded to the user whose message caused the function to be called. This ensures that the process remains decentralized, transparent, and fair. 🎉

2. Launch an agent:

2.1 Choose how would you like to create your agent

Screenshot 2025-02-01 at 20.36.38.png

2.2 Prompt Launch

Describe your agent's personality and behavior. Our AI will generate a complete agent configuration based on your description.

Screenshot 2025-02-01 at 20.38.21.png

2.3 Quick Creation

Create a simple "Secret Phrase" challenge with default options.

Screenshot 2025-02-01 at 20.38.42.png

2.4 Advanced Creation

Multiple configurations + function calls:

Advanced Creation Tutorial

2.5 API Integration

Submit the form and we will create a custom integration with your API.

📜 Settings & Rules

Each tournament has unique rules, including:

  • Custom Prize Pools
  • Message Pricing
  • Expiry Settings

🔗 Useful Links

Feedback & Support

Feel free to reach out at dev@jailbreakme.xyz for feedback or support.

Jailbreak the World 🦍