Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities

Name: Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities
Duration: 15 min
Description: Talk from 34th USENIX Security Symposium (USENIX Security '25).

Yiting Qu

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