{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/injecting-bias-in-text-to-image-models-via","title":"Backdooring Bias into Text-to-Image Models","arxiv_id":"2406.15213","date":"2024-06-21","proceeding":null,"authors":["Ali Naseh","Jaechul Roh","Eugene Bagdasaryan","Amir Houmansadr"],"abstract":"Text-conditional diffusion models, i.e. text-to-image, produce eye-catching images that represent descriptions given by a user. These images often depict benign concepts but could also carry other purposes. Specifically, visual information is easy to comprehend and could be weaponized for propaganda -- a serious challenge given widespread usage and deployment of generative models. In this paper, we show that an adversary can add an arbitrary bias through a backdoor attack that would affect even benign users generating images. While a user could inspect a generated image to comply with the given text description, our attack remains stealthy as it preserves semantic information given in the text prompt. Instead, a compromised model modifies other unspecified features of the image to add desired biases (that increase by 4-8x). Furthermore, we show how the current state-of-the-art generative models make this attack both cheap and feasible for any adversary, with costs ranging between $12-$18. We evaluate our attack over various types of triggers, adversary objectives, and biases and discuss mitigations and future work. Our code is available at https://github.com/jrohsc/Backdororing_Bias.","url_abs":"https://arxiv.org/abs/2406.15213v2","url_pdf":"https://arxiv.org/pdf/2406.15213v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"injecting-bias-in-text-to-image-models-via","repo_url":"https://github.com/jrohsc/backdororing_bias","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"backdoor-attack","task_name":"Backdoor Attack"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2406.15213","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}