Timezone: »

Raising the Cost of Malicious AI-Powered Image Editing
Hadi Salman · Alaa Khaddaj · Guillaume Leclerc · Andrew Ilyas · Aleksander Madry

Tue Jul 25 08:30 PM -- 08:38 PM (PDT) @ Meeting Room 313
Event URL: https://gradientscience.org/photoguard/ »

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.

Author Information

Hadi Salman (OpenAI / MIT)
Alaa Khaddaj (MIT)
Guillaume Leclerc (MIT)
Andrew Ilyas (MIT)
Aleksander Madry (MIT)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors