LLM-Prompt-Vulnerabilities icon indicating copy to clipboard operation
LLM-Prompt-Vulnerabilities copied to clipboard

Published 20 hours ago • verified publisher icon promptslab
→

Metadata

Prompts Methods to find the vulnerabilities in Generative Models

LLM & Prompt Vulnerabilities

Finding and documentating vulnerabilities in Generative Models based on prompt-engineering

http://makeapullrequest.com Community

Name Description proof
Prompt In the Middle (PITM)? Injecting prompt to access other's output [Proof]
Nested Prompt Attack (Need a better name :D) While Providing nested prompts, the model ignores the initial instructions [Proof]

← Metadata

16
Stars
2
Forks
Watchers

Owner

verified publisher icon promptslab

Metadata

Prompts Methods to find the vulnerabilities in Generative Models

Back