@inproceedings{c07d0289803449299bbd02c99435cfa7,
title = "RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation with Natural Prompts",
abstract = "The field of text-to-image generation has made remarkable strides in creating high-fidelity and photorealistic images. As this technology gains popularity, there is a growing concern about its potential security risks. However, there has been limited exploration into the robustness of these models from an adversarial perspective. Existing research has primarily focused on untargeted settings, and lacks holistic consideration for reliability (attack success rate) and stealthiness (imperceptibility). In this paper, we propose RIATIG, a reliable and imperceptible adversarial attack against text-to-image models via inconspicuous examples. By formulating the example crafting as an optimization process and solving it using a genetic-based method, our proposed attack can generate imperceptible prompts for text-to-image generation models in a reliable way. Evaluation of six popular text-to-image generation models demonstrates the efficiency and stealthiness of our attack in both white-box and black-box settings.",
keywords = "Adversarial attack and defense",
author = "Han Liu and Yuhao Wu and Shixuan Zhai and Bo Yuan and Ning Zhang",
note = "Publisher Copyright: {\textcopyright}2023 IEEE.; 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 ; Conference date: 18-06-2023 Through 22-06-2023",
year = "2023",
doi = "10.1109/CVPR52729.2023.01972",
language = "American English",
isbn = "9798350301298",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "20585--20594",
booktitle = "Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023",
address = "United States",
}