Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909055292801024 |
|---|---|
| author | Rastogi, Charvi Bhutani, Mukul Kahng, Minsuk Muhammad, Shamsuddeen Hassan Razumovskaia, Evgeniia Suresh, Priyanka Ahmad, Ibrahim Said Kalia, Charu Mahomed, Yaaseen Maji, Madhurima Lee, Minjae Parrish, Alicia Quaye, Jessica Reddi, Vijay Janapa Verma, Aishwarya Aroyo, Lora |
| author_facet | Rastogi, Charvi Bhutani, Mukul Kahng, Minsuk Muhammad, Shamsuddeen Hassan Razumovskaia, Evgeniia Suresh, Priyanka Ahmad, Ibrahim Said Kalia, Charu Mahomed, Yaaseen Maji, Madhurima Lee, Minjae Parrish, Alicia Quaye, Jessica Reddi, Vijay Janapa Verma, Aishwarya Aroyo, Lora |
| contents | Despite the global deployment of text-to-image (T2I) models, their safety frameworks are largely calibrated to a Western-centric default, creating significant vulnerabilities for the rest of the world. To embrace cultural pluralism and bring historically under-represented perspectives in T2I safety, we conduct localised community-centered red teaming studies in the Global South. Our two-fold approach prioritizes localization and participation, by focusing on secondary urban centers in these regions, and conducting community engagement and training workshops to contextualize local norms. As a result, we present PLACES, a dataset comprising over 26,000 examples of T2I model failures collected in partnership with universities in Ghana, Nigeria, and two regions of India (Karnataka and Punjab). Analysis of prompts collected reveals a wide-ranging diversity in socio-cultural and linguistic attributes, when compared to existing geography-agnostic crowdsourced red-teaming data. We observe unique adversarial patterns enabled by local cultural and linguistic nuances, and distinct clusters within region around specific themes, such as religion in India. Moreover, we uncover structural contextual gaps in existing safety frameworks by identifying novel harms showing normative dissonance (e.g., violating religious norms, ignoring local customs, and ominous symbolism). This work argues that expanding T2I safety requires moving beyond mere scale to incorporate deeply localised, participatory methodologies for data collection and contextualization. Content warning: This paper includes examples containing potentially harmful or offensive content. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_19190 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South Rastogi, Charvi Bhutani, Mukul Kahng, Minsuk Muhammad, Shamsuddeen Hassan Razumovskaia, Evgeniia Suresh, Priyanka Ahmad, Ibrahim Said Kalia, Charu Mahomed, Yaaseen Maji, Madhurima Lee, Minjae Parrish, Alicia Quaye, Jessica Reddi, Vijay Janapa Verma, Aishwarya Aroyo, Lora Computers and Society Artificial Intelligence Human-Computer Interaction Despite the global deployment of text-to-image (T2I) models, their safety frameworks are largely calibrated to a Western-centric default, creating significant vulnerabilities for the rest of the world. To embrace cultural pluralism and bring historically under-represented perspectives in T2I safety, we conduct localised community-centered red teaming studies in the Global South. Our two-fold approach prioritizes localization and participation, by focusing on secondary urban centers in these regions, and conducting community engagement and training workshops to contextualize local norms. As a result, we present PLACES, a dataset comprising over 26,000 examples of T2I model failures collected in partnership with universities in Ghana, Nigeria, and two regions of India (Karnataka and Punjab). Analysis of prompts collected reveals a wide-ranging diversity in socio-cultural and linguistic attributes, when compared to existing geography-agnostic crowdsourced red-teaming data. We observe unique adversarial patterns enabled by local cultural and linguistic nuances, and distinct clusters within region around specific themes, such as religion in India. Moreover, we uncover structural contextual gaps in existing safety frameworks by identifying novel harms showing normative dissonance (e.g., violating religious norms, ignoring local customs, and ominous symbolism). This work argues that expanding T2I safety requires moving beyond mere scale to incorporate deeply localised, participatory methodologies for data collection and contextualization. Content warning: This paper includes examples containing potentially harmful or offensive content. |
| title | Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South |
| topic | Computers and Society Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2605.19190 |