Privacy preserving face recognition using secure multi party computation
GhostFaceMPC: Privacy-Preserving Face Recognition with Multi-Party Computation
Cryptography and Security
Summary
Facial recognition systems help identify people but raise privacy concerns because they handle sensitive images and biometric data. The authors designed GhostFaceMPC, a system that keeps face recognition private by processing data without ever revealing raw images or feature details. They made a special version of a face recognition model that works efficiently with secure multi-party computation, so multiple parties can jointly do recognition without sharing private data. This approach helps protect user privacy at every step, from image processing to matching.
What this means in practice
- •For security system developers: Build authentication systems that perform face recognition without exposing sensitive biometric data to anyone involved.$Commercial implications: Enables creation of privacy-focused commercial security products for organizations needing biometric verification without raw data exposure.
- •For cloud service engineers: Deploy face recognition services on cloud platforms that process encrypted facial data securely among multiple parties.
Authors
Davide Carnemolla, Dario Catalano, Mario Di Raimondo
Abstract
Facial recognition has become central to modern authentication systems, security frameworks, and personalized services. However, its widespread adoption is hindered by severe privacy risks, particularly surrounding unauthorized access to sensitive biometric data. To address these challenges, this paper presents GhostFaceMPC, the first end-to-end, privacy-preserving face recognition system to evaluate a deep convolutional neural network extractor and matching under secure multi-party computation. GhostFaceMPC enables secure processing of facial data across all stages of a face recognition process, from feature extraction and storage to matching, without exposing raw images or biometric embeddings at any stage. We introduce a multi-party computation-friendly quantization of the GhostFaceNet model and circuit optimizations that make face recognition under multi-party computation practical. The code is available at https://github.com/crypto-unict/GhostFaceMPC.