Leaked GPTs Prompts Bypass the 25 message limit or to try out GPTs without a Plus subscription.
Whistleblower is a offensive security tool for testing against system prompt leakage and capability discovery of an AI application exposed through API. Built for AI engineers, security researchers and folks who want to know what's going on inside the LLM-based app they use daily
A prompt injection game to collect data for robust ML research
Categorizes AI jailbreak tactics using taxonomic analysis to enhance LLM security measures.
MetaSC: Test-Time Safety Specification Optimization for Language Models
π Analyze system prompts in large language models to understand design principles and enhance AI application effectiveness.
Add a description, image, and links to the jailbreaks topic page so that developers can more easily learn about it.
To associate your repository with the jailbreaks topic, visit your repo's landing page and select "manage topics."