Davide Carnemolla, D Catalano, Mario Di Raimondo · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.29987 · cited by 0 works (OpenAlex) · open-access PDF
La reconnaissance faciale est devenue un élément central des systèmes d'authentification modernes, des cadres de sécurité et des services personnalisés. Cependant, son adoption généralisée est entravée par de graves risques de confidentialité, en particulier autour de l'accès non autorisé aux données biométriques sensibles. Pour relever ces défis, ce document présente GhostFaceMPC, le premier système de reconnaissance faciale de bout en bout, qui préserve la vie privée pour évaluer un extracteur de réseau neuronal profond convolutif et correspondre sous un calcul sécurisé multipartite. GhostFaceMPC permet le traitement sécurisé des données faciales à travers toutes les étapes d'un processus de reconnaissance faciale, de l'extraction de fonctionnalités et du stockage à la correspondance
Machine translation (Meta M2M100); the English original follows.
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.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Facial recognition system, Biometrics, Artificial intelligence, Convolutional neural network, Feature extraction
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29987, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange