Harm Amplification in Text-to-Image Models

1 February 2024

Papers citing "Harm Amplification in Text-to-Image Models"

9 / 9 papers shown

Title
SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model Yongting Zhang Lu Chen Guodong Zheng Yifeng Gao Rui Zheng ... Yu Qiao Xuanjing Huang Feng Zhao Tao Gui Jing Shao VLM 55 22 0 17 Jun 2024
SoUnD Framework: Analyzing (So)cial Representation in (Un)structured (D)ata Mark Díaz Sunipa Dev Emily Reif Remi Denton Vinodkumar Prabhakaran 20 3 0 28 Nov 2023
Social Biases through the Text-to-Image Generation Lens Ranjita Naik Besmira Nushi 83 111 0 30 Mar 2023
From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible ML Shalaleh Rismani Renee Shelby A. Smart Edgar W. Jatho Joshua A. Kroll AJung Moon Negar Rostamzadeh 19 19 0 06 Oct 2022
Red-Teaming the Stable Diffusion Safety Filter Javier Rando Daniel Paleka David Lindner Lennard Heim Florian Tramèr DiffM 116 179 0 03 Oct 2022
Data Feedback Loops: Model-driven Amplification of Dataset Biases Rohan Taori Tatsunori B. Hashimoto 53 42 0 08 Sep 2022
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models Jaemin Cho Abhaysinh Zala Mohit Bansal ViT 121 167 0 08 Feb 2022
A Systematic Study of Bias Amplification Melissa Hall L. V. D. van der Maaten Laura Gustafson Maxwell Jones Aaron B. Adcock 72 69 0 27 Jan 2022
A Survey on Bias and Fairness in Machine Learning Ninareh Mehrabi Fred Morstatter N. Saxena Kristina Lerman Aram Galstyan SyDa FaML 280 3,347 0 23 Aug 2019