Abstract
Smartphones are moving towards the fullscreen 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 multiple-pixel perturbation. For face recognition, the average accuracy drops from 91% to merely 1.8% and 0.25%, respectively.
Original language | English |
---|---|
Title of host publication | ACM MobiCom '23: Proceedings of the 29th Annual International Conference on Mobile Computing and Networking |
Place of Publication | New York |
Publisher | Association for Computing Machinery (ACM) |
Pages | 1-16 |
Number of pages | 16 |
ISBN (Print) | 978-1-4503-9990-6 |
DOIs | |
Publication status | Published - 2023 |
Event | ACM MobiCom '23: The 29th Annual International Conference on Mobile Computing and Networking - Madrid, Spain Duration: 2 Oct 2023 → 6 Oct 2023 Conference number: 29th |
Conference
Conference | ACM MobiCom '23 |
---|---|
Country/Territory | Spain |
City | Madrid |
Period | 2/10/23 → 6/10/23 |
Keywords
- Under-screen camera
- adversarial perturbation
- privacy