Cross-Modal Prompt Inversion: Unifying Threats to Text and Image Generative AI Models

Name: Cross-Modal Prompt Inversion: Unifying Threats to Text and Image Generative AI Models
Duration: 15 min
Description: Talk from 34th USENIX Security Symposium (USENIX Security '25).

Dayong Ye

34th USENIX Security Symposium (USENIX Security '25) · Day 2 · LLM Security 2: Jailbreaking and Prompt Stealing