.png){kind=icon}
Return
Efficient Privacy-Preserving Face Identification Protocol
.png){kind=icon}
PRE
AI
DOI：10.1109/TSC.2023.3242285.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Face identification is an important research topic in artificial intelligence and it has wide application in civilian and law enforcement scenarios that require reliable biometric identification. However, the wide deployment of face identification systems has raised serious privacy concerns about the abuse of users' face images. In this paper, we propose an efficient privacy-preserving face identification protocol based on fully homomorphic encryption and garbled circuit. Our work is the first privacy-preserving face identification protocol that guarantees the privacy of the users' face images such that the server cannot learn any information about the face images, access pattern and identification result, while providing face identification service. We formally prove the security of our protocol in a semi-honest model. Experimental results the practicality of our protocol for the large face images database.
Keywords:
Computation over encrypted data
face identification
fully homomorphic encryption
garbled circuit
privacy-preserving computation
Journal
IF:
5.8
Papers:
2.2K
Citations:
6.5K
Organization
Cited Papers
.png){kind=icon}
ShareSave
ShareSavePractical Privacy-Preserving Face Authentication for Smartphones Secure Against Malicious Clients
PREAI
ShareSave
View more