2023-04-24-saravanan23a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models	Text-to-image diffusion models have been adopted into key commercial workflows, such as art generation and image editing. Characterizing the implicit social biases they exhibit, such as gender and racial stereotypes, is a necessary first step in avoiding discriminatory outcomes. While existing studies on social bias focus on image generation, the biases exhibited in alternate applications of diffusion-based foundation models remain under-explored. We propose a framework that uses synthetic images to probe two applications of diffusion models, image editing and classification, for social bias. Using our framework, we uncover meaningful and significant inter-sectional social biases in Stable Diffusion, a state-of-the-art open-source text-to-image model. Our findings caution against the uninformed adoption of text-to-image foundation models for downstream tasks and services.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	saravanan23a	0	Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models	84	102	84-102	84	false	Saravanan, Adhithya Prakash and Kocielnik, Rafal and Jiang, Roy and Han, Pengrui and Anandkumar, Anima	given family Adhithya Prakash Saravanan given family Rafal Kocielnik given family Roy Jiang given family Pengrui Han given family Anima Anandkumar	2023-04-24		Proceedings on "I Can't Believe It's Not Better: Failure Modes in the Age of Foundation Models" at NeurIPS 2023 Workshops	239	inproceedings	date-parts 2023 4 24	https://proceedings.mlr.press/v239/saravanan23a/saravanan23a.pdf