On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts

Name: On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts
Duration: 15 min
Description: Talk from 34th USENIX Security Symposium (USENIX Security '25).

Yixin Wu

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