Jailbreak Dev

GitHub profile

Twitter profile

@jailbreak

Jailbreak Dev

@jailbreak

Solidity

JavaScript

Node.js

TypeScript

React.js

New York, United States

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 🏆

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:

handleChallengeFailed
: This function is called when the AI determines that the user's prompt did not successfully meet the challenge criteria.
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. 🎉