paper-with-me

Papers

Inverting Black-Box Face Recognition Systems via Zero-Order Optimization in Eigenface Space

2025-06-11 · Anton Razzhigaev, Matvey Mikhalchuk, Klim Kireev, Igor Udovichenko, Andrey Kuznetsov, Aleksandr Petiushko

Reconstructing facial images from black-box recognition models poses a significant privacy threat. While many methods require access to embeddings, we address the more challenging scenario of model inversion using only similarity scores. This paper introduces DarkerBB, a novel approach that reconstructs color faces by performing zero-order optimization within a PCA-derived eigenface space. Despite this highly limited information, experiments on LFW, AgeDB-30, and CFP-FP benchmarks demonstrate that DarkerBB achieves state-of-the-art verification accuracies in the similarity-only setting, with competitive query efficiency.

📄 PDF Abstract BibTeX arXiv:2506.09777

Code (1)

fusionbrainlab/adversarialfaces 공식 구현 pytorch

Tasks

Face Recognition

Similar Papers 제목 키워드 기반

Approximating Optimal Morphing Attacks using Template Inversion

2024-02-01 · Laurent Colbois, Hatef Otroshi Shahreza, Sébastien Marcel

Recent works have demonstrated the feasibility of inverting face recognition systems, enabling to recover convincing face images using only their embeddings. We leverage such template inversion models to develop a novel …

Face RecognitionMORPH

Controllable Inversion of Black-Box Face Recognition Models via Diffusion

2023-03-23 · Manuel Kansy, Anton Raël, Graziana Mignone, Jacek Naruniec 외

Face recognition models embed a face image into a low-dimensional identity vector containing abstract encodings of identity-specific facial features that allow individuals to be distinguished from one another. We tackle …

DenoisingDiversityFace Recognition

Real-World Transferable Adversarial Attack on Face-Recognition Systems

2025-09-27 · Andrey Kaznacheev, Matvey Mikhalchuk, Andrey Kuznetsov, Aleksandr Petiushko 외 arxiv

Adversarial attacks on face recognition (FR) systems pose a significant security threat, yet most are confined to the digital domain or require white-box access. We introduce GaP (Gaussian Patch), a novel method to gener…

Adversarial AttackFace Recognition

Is Face Recognition Safe from Realizable Attacks?

2022-10-15 · Sanjay Saha, Terence Sim

Face recognition is a popular form of biometric authentication and due to its widespread use, attacks have become more common as well. Recent studies show that Face Recognition Systems are vulnerable to attacks and can l…

Face Recognition

RSTAM: An Effective Black-Box Impersonation Attack on Face Recognition using a Mobile and Compact Printer

2022-06-25 · Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie

Face recognition has achieved considerable progress in recent years thanks to the development of deep neural networks, but it has recently been discovered that deep neural networks are vulnerable to adversarial examples.…

Face Recognition