I conducted an authorized AI security assessment of Lily Cybersecurity 7B to evaluate how effecti...I conducted an authorized AI security assessment of Lily Cybersecurity 7B to evaluate how effecti...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Stephen's avatar
Stephen Kisong'e
• 13h
I conducted an authorized AI security assessment of Lily Cybersecurity 7B to evaluate how effectively a hardened system prompt could resist jailbreak and prompt injection attacks.
Using Prompt Fuzzer, I ran 15 attack techniques against the model. The system prompt successfully blocked 8 attempts, including most roleplay and social engineering attacks. The successful bypasses mainly used translated or altered wording to disguise the intent of the request.
This project demonstrates why system prompts should be supported by input validation, moderation, output filtering, and continuous AI red team testing.
AI Engineer CybersecuritySecurity EngineeringBashGitHub
Post image
Back to feed
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started