Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models

arXiv:2605.26332v2 Announce Type: replace-cross Abstract: Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been introduced to make the model generate such unlearned concepts. These attacks, nevertheless, do not assume a realistic threat model, i.e. they either assume access to the model weights, or result in gibberish adversarial prompts that could be easily detected even through naive rule-based safeguarding. We aim to address this gap in this paper. We introduce BEAP, a black-box, embedding-aware adversarial prompting attack that leverages a large language model (LLM) to iteratively generate effective adversarial prompts and exploit such hidden vulnerabilities. BEAP performs an embedding-aware search in text space, combining multiple reward signals: unlearned concept presence, text-image alignment, and image quality, to refine generated prompts. Unlike previous attack methods, BEAP keeps its prompts undetectable to safety filters while producing high-quality images. Across five unlearning methods, BEAP achieves a macro-averaged ASR of 97.8% under the held-out OpenNSFW2 evaluation, exceeding the white-box UDA baseline by 41.6 percentage points (56.2% to 97.8%). Counting unsuccessful searches at the full 100-query budget, BEAP uses 32.1 image-generation queries per evaluated prompt on average under this criterion.

Abstract:Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been introduced to make the model generate such unlearned concepts. These attacks, nevertheless, do not assume a realistic threat model, i.e. they either assume access to the model weights, or result in gibberish adversarial prompts that could be easily detected even through naive rule-based safeguarding. We aim to address this gap in this paper. We introduce BEAP, a black-box, embedding-aware adversarial prompting attack that leverages a large language model (LLM) to iteratively generate effective adversarial prompts and exploit such hidden vulnerabilities. BEAP performs an embedding-aware search in text space, combining multiple reward signals: unlearned concept presence, text-image alignment, and image quality, to refine generated prompts. Unlike previous attack methods, BEAP keeps its prompts undetectable to safety filters while producing high-quality images. Across five unlearning methods, BEAP achieves a macro-averaged ASR of 97.8% under the held-out OpenNSFW2 evaluation, exceeding the white-box UDA baseline by 41.6 percentage points (56.2% to 97.8%). Counting unsuccessful searches at the full 100-query budget, BEAP uses 32.1 image-generation queries per evaluated prompt on average under this criterion.

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)

arXiv:2605.26332 [cs.CV]

(or arXiv:2605.26332v2 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2605.26332 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models

Related coverage