arXiv AI By Ye Leng, Junjie Chu, Yiting Qu, Mingjie Li, Yun Shen, Yang Zhang

Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation

Read the original on arXiv AI →

arXiv:2608. 05210v1 Announce Type: cross Abstract: Picture books and comics have long been used to disseminate hateful narratives because they are easily understood even by children, as exemplified by the notorious Nazi propaganda picture book \emph{Der Giftpilz}.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning
Jun 17

Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Models

arXiv:2403. 18957v3 Announce Type: replace-cross Abstract: Online user generated content games (UGCGs) are increasingly popular among children and adolescents for social interaction and more creative online entertainment.

By Keyan Guo, Ayush Utkarsh, Wenbo Ding, Isabelle Ondracek, Ziming Zhao, Guo Freeman, Nishant Vishwamitra, Hongxin Hu
Hugging Face Trending Papers
Jul 7

AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models

Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit content. Existing alignment paradigms, from input sanitization to structural feature pruning, are largely organized around unsafe concepts explicitly exposed during filtering, editing, or localization.