|
- UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI . . .
In this work, we propose UnsafeBench, a benchmarking framework that evaluates the effectiveness and robustness of image safety classifiers, with a particular focus on the impact of AI-generated images on their performance
- GitHub - YitingQu UnsafeBench
UnsafeBench is a comprehensive evaluation framework for assessing the safety and robustness of Vision-Language Models (VLMs) and image safety classifiers against unsafe content
- UnsafeBench
UnsafeBench We propose UnsafeBench, a benchmarking framework that evaluates the effectiveness and robustness of image safety classifiers, i e , five conventional classifiers and three VLM-based classifiers Insights
- yiting UnsafeBench · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science
- UnsafeBench|图像安全分类数据集|内容审核数据集
UnsafeBench数据集主要用于评估和比较图像安全分类器在现实世界和AI生成图像中的有效性和鲁棒性。 通过这个数据集，研究人员可以测试和评估现有的图像安全分类器，以及基于视觉语言模型（VLMs）的分类器，以了解它们在不同类型的不安全图像上的表现。
- UnsafeBench: Benchmarking Image Safety Classifiers
We establish UnsafeBench, a benchmarking framework that comprehensively evaluates the effectiveness and robustness of image safety classifiers on both real-world and AI-generated images
- Publications - Yiting Qu (瞿艺婷)
UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images Yiting Qu, Xinyue Shen, Yixin Wu, Michael Backes, Savvas Zannettou, Yang Zhang; CCS 2025
- UnsafeBench: Benchmarking Image Safety Classifiers on Real . . . - Zenodo
UnsafeBench is a comprehensive evaluation framework for assessing the safety and robustness of image safety classifiers and VLMs against unsafe images
|
|
|