Skip to main content

11 posts tagged with "security-vulnerability"

View All Tags

Automated Jailbreaking Techniques with DALL-E: Complete Red Team Guide

Ian Webster
Engineer & OWASP Gen AI Red Teaming Contributor

We all know that image models like OpenAI's Dall-E can be jailbroken to generate violent, disturbing, and offensive images. It turns out this process can be fully automated.

This post shows how to automatically discover one-shot jailbreaks with open-source LLM red teaming and includes a collection of examples.

llm image red teaming