SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.10571 · 2024

Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

FunctionStatusWhere it lives
collate_fn Ran vancyland/prompt-agnostic-adversarial-perturbation-for-customized-diffusion-models.github.io/train_dreambooth.py
pointer only (licence: GPL-3.0) · get_code("229d634611bdc645")
load_data Ran vancyland/prompt-agnostic-adversarial-perturbation-for-customized-diffusion-models.github.io/attack/papv1.py
pointer only (licence: GPL-3.0) · get_code("686a5a7fc55acb4e")
import_model_class_from_model_name_or_path Not yet run vancyland/prompt-agnostic-adversarial-perturbation-for-customized-diffusion-models.github.io/train_dreambooth.py
pointer only (licence: GPL-3.0) · get_code("2f00b39db5a81466")
parse_args Not yet run vancyland/prompt-agnostic-adversarial-perturbation-for-customized-diffusion-models.github.io/train_dreambooth.py
pointer only (licence: GPL-3.0) · get_code("d0510f45e1460c48")
parse_args Not yet run vancyland/prompt-agnostic-adversarial-perturbation-for-customized-diffusion-models.github.io/attack/papv1.py
pointer only (licence: GPL-3.0) · get_code("66e7662142d90765")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Diffusion models have revolutionized customized text-to-image generation, allowing for efficient synthesis of photos from personal data with textual descriptions. However, these advancements bring forth risks including privacy breaches and unauthorized replication of artworks. Previous researches primarily center around using prompt-specific methods to generate adversarial examples to protect personal images, yet the effectiveness of existing methods is hindered by constrained adaptability to different prompts. In this paper, we introduce a Prompt-Agnostic Adversarial Perturbation (PAP) method for customized diffusion models. PAP first models the prompt distribution using a Laplace Approximation, and then produces prompt-agnostic perturbations by maximizing a disturbance expectation based on the modeled distribution. This approach effectively tackles the prompt-agnostic attacks, leading to improved defense stability. Extensive experiments in face privacy and artistic style protection, demonstrate the superior generalization of PAP in comparison to existing techniques. Our project page is available at https://github.com/vancyland/Prompt-Agnostic-Adversarial-Perturbation-for-Customized-Diffusion-Models.github.io.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.10571")
get_code_for_paper("2408.10571")
have("2408.10571")

Connect an agent — have() is free.