@InProceedings{pmlr-v202-salman23a,
title = {Raising the Cost of Malicious AI-Powered Image Editing},
author = {Salman, Hadi and Khaddaj, Alaa and Leclerc, Guillaume and Ilyas, Andrew and Madry, Aleksander},
booktitle = {Proceedings of the 40th International Conference on Machine Learning},
pages = {29894--29918},
year = {2023},
editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan},
volume = {202},
series = {Proceedings of Machine Learning Research},
month = {Jul},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v202/salman23a/salman23a.pdf},
url = {https://proceedings.mlr.press/v202/salman23a.html},
abstract = {We present an approach to mitigating the risks of malicious image editing posed by large diffusion models. The key idea is to immunize images so as to make them resistant to manipulation by these models. This immunization relies on injection of imperceptible adversarial perturbations designed to disrupt the operation of the targeted diffusion models, forcing them to generate unrealistic images. We provide two methods for crafting such perturbations, and then demonstrate their efficacy. Finally, we discuss a policy component necessary to make our approach fully effective and practical—one that involves the organizations developing diffusion models, rather than individual users, to implement (and support) the immunization process.}
}
