Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Quaye, Jessica, Parrish, Alicia, Inel, Oana, Rastogi, Charvi, Kirk, Hannah Rose, Kahng, Minsuk, van Liemt, Erin, Bartolo, Max, Tsang, Jess, White, Justin, Clement, Nathan, Mosquera, Rafael, Ciro, Juan, Reddi, Vijay Janapa, Aroyo, Lora
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909201463246848
author Quaye, Jessica
Parrish, Alicia
Inel, Oana
Rastogi, Charvi
Kirk, Hannah Rose
Kahng, Minsuk
van Liemt, Erin
Bartolo, Max
Tsang, Jess
White, Justin
Clement, Nathan
Mosquera, Rafael
Ciro, Juan
Reddi, Vijay Janapa
Aroyo, Lora
author_facet Quaye, Jessica
Parrish, Alicia
Inel, Oana
Rastogi, Charvi
Kirk, Hannah Rose
Kahng, Minsuk
van Liemt, Erin
Bartolo, Max
Tsang, Jess
White, Justin
Clement, Nathan
Mosquera, Rafael
Ciro, Juan
Reddi, Vijay Janapa
Aroyo, Lora
contents With the rise of text-to-image (T2I) generative AI models reaching wide audiences, it is critical to evaluate model robustness against non-obvious attacks to mitigate the generation of offensive images. By focusing on ``implicitly adversarial'' prompts (those that trigger T2I models to generate unsafe images for non-obvious reasons), we isolate a set of difficult safety issues that human creativity is well-suited to uncover. To this end, we built the Adversarial Nibbler Challenge, a red-teaming methodology for crowdsourcing a diverse set of implicitly adversarial prompts. We have assembled a suite of state-of-the-art T2I models, employed a simple user interface to identify and annotate harms, and engaged diverse populations to capture long-tail safety issues that may be overlooked in standard testing. The challenge is run in consecutive rounds to enable a sustained discovery and analysis of safety pitfalls in T2I models. In this paper, we present an in-depth account of our methodology, a systematic study of novel attack strategies and discussion of safety failures revealed by challenge participants. We also release a companion visualization tool for easy exploration and derivation of insights from the dataset. The first challenge round resulted in over 10k prompt-image pairs with machine annotations for safety. A subset of 1.5k samples contains rich human annotations of harm types and attack styles. We find that 14% of images that humans consider harmful are mislabeled as ``safe'' by machines. We have identified new attack strategies that highlight the complexity of ensuring T2I model robustness. Our findings emphasize the necessity of continual auditing and adaptation as new vulnerabilities emerge. We are confident that this work will enable proactive, iterative safety assessments and promote responsible development of T2I models.
format Preprint
id arxiv_https___arxiv_org_abs_2403_12075
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation
Quaye, Jessica
Parrish, Alicia
Inel, Oana
Rastogi, Charvi
Kirk, Hannah Rose
Kahng, Minsuk
van Liemt, Erin
Bartolo, Max
Tsang, Jess
White, Justin
Clement, Nathan
Mosquera, Rafael
Ciro, Juan
Reddi, Vijay Janapa
Aroyo, Lora
Computers and Society
Artificial Intelligence
Cryptography and Security
Computer Vision and Pattern Recognition
Machine Learning
With the rise of text-to-image (T2I) generative AI models reaching wide audiences, it is critical to evaluate model robustness against non-obvious attacks to mitigate the generation of offensive images. By focusing on ``implicitly adversarial'' prompts (those that trigger T2I models to generate unsafe images for non-obvious reasons), we isolate a set of difficult safety issues that human creativity is well-suited to uncover. To this end, we built the Adversarial Nibbler Challenge, a red-teaming methodology for crowdsourcing a diverse set of implicitly adversarial prompts. We have assembled a suite of state-of-the-art T2I models, employed a simple user interface to identify and annotate harms, and engaged diverse populations to capture long-tail safety issues that may be overlooked in standard testing. The challenge is run in consecutive rounds to enable a sustained discovery and analysis of safety pitfalls in T2I models. In this paper, we present an in-depth account of our methodology, a systematic study of novel attack strategies and discussion of safety failures revealed by challenge participants. We also release a companion visualization tool for easy exploration and derivation of insights from the dataset. The first challenge round resulted in over 10k prompt-image pairs with machine annotations for safety. A subset of 1.5k samples contains rich human annotations of harm types and attack styles. We find that 14% of images that humans consider harmful are mislabeled as ``safe'' by machines. We have identified new attack strategies that highlight the complexity of ensuring T2I model robustness. Our findings emphasize the necessity of continual auditing and adaptation as new vulnerabilities emerge. We are confident that this work will enable proactive, iterative safety assessments and promote responsible development of T2I models.
title Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation
topic Computers and Society
Artificial Intelligence
Cryptography and Security
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2403.12075