Paper ID: 2404.19382

Probing Unlearned Diffusion Models: A Transferable Adversarial Attack Perspective

Xiaoxuan Han, Songlin Yang, Wei Wang, Yang Li, Jing Dong

Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these involved concepts from diffusion models. However, these unlearning methods only shift the text-to-image mapping and preserve the visual content within the generative space of diffusion models, leaving a fatal flaw for restoring these erased concepts. This erasure trustworthiness problem needs probe, but previous methods are sub-optimal from two perspectives: (1) Lack of transferability: Some methods operate within a white-box setting, requiring access to the unlearned model. And the learned adversarial input often fails to transfer to other unlearned models for concept restoration; (2) Limited attack: The prompt-level methods struggle to restore narrow concepts from unlearned models, such as celebrity identity. Therefore, this paper aims to leverage the transferability of the adversarial attack to probe the unlearning robustness under a black-box setting. This challenging scenario assumes that the unlearning method is unknown and the unlearned model is inaccessible for optimization, requiring the attack to be capable of transferring across different unlearned models. Specifically, we employ an adversarial search strategy to search for the adversarial embedding which can transfer across different unlearned models. This strategy adopts the original Stable Diffusion model as a surrogate model to iteratively erase and search for embeddings, enabling it to find the embedding that can restore the target concept for different unlearning methods. Extensive experiments demonstrate the transferability of the searched adversarial embedding across several state-of-the-art unlearning methods and its effectiveness for different levels of concepts.

Submitted: Apr 30, 2024