Exposing the Guardrails: Reverse-Engineering and Jailbreaking Safety Filters in DALL·E Text-to-Image Pipelines

Name: Exposing the Guardrails: Reverse-Engineering and Jailbreaking Safety Filters in DALL·E Text-to-Image Pipelines
Duration: 15 min
Description: Talk from 34th USENIX Security Symposium (USENIX Security '25).

Corban Villa

34th USENIX Security Symposium (USENIX Security '25) · Day 1 · ML and AI Security 1: Images