Published October 16, 2023 | Version Author's version
Conference paper Open

Screen Perturbation: Adversarial Atack and Defense on Under-Screen Camera


Smartphones are moving towards the full-screen design for better user experience. This trend forces front cameras to be placed under screen, leading to Under-Screen Cameras (USC). Accordingly, a small area of the screen is made translucent to allow light to reach the USC. In this paper, we utilize the translucent screen's features to inconspicuously modify its pixels, imperceptible to human eyes but inducing perturbations on USC images. These screen perturbations affect deep learning models in image classification and face recognition. They can be employed to protect user privacy, or disrupt the front camera's functionality in the malicious case. We design two methods, one-pixel perturbation and multiple-pixel perturbation, that can add screen perturbations to images captured by USC and successfully fool various deep learning models. Our evaluations, with three commercial full-screen smartphones on testbed datasets and synthesized datasets, show that screen perturbations significantly decrease the average image classification accuracy, dropping from 85% to only 14% for one-pixel perturbation and 5.5% for multiplepixel perturbation. For face recognition, the average accuracy drops from 91% to merely 1.8% and 0.25%, respectively 


Hanting - UnderDisplayCamera_Security zenodo.pdf

Files (1.4 MB)

Additional details


ENLIGHTEM – European Training Network in Low-energy Visible Light IoT Systems 814215
European Commission