From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language Models

Name: From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language Models
Duration: 15 min
Description: Talk from 34th USENIX Security Symposium (USENIX Security '25).

Yihan Ma

34th USENIX Security Symposium (USENIX Security '25) · Day 2 · ML and AI Security 2