paper-with-me

Papers

Universal Adversarial Spoofing Attacks against Face Recognition

2021-10-02 · Takuma Amada, Seng Pei Liew, Kazuya Kakizaki, Toshinori Araki

We assess the vulnerabilities of deep face recognition systems for images that falsify/spoof multiple identities simultaneously. We demonstrate that, by manipulating the deep feature representation extracted from a face image via imperceptibly small perturbations added at the pixel level using our proposed Universal Adversarial Spoofing Examples (UAXs), one can fool a face verification system into recognizing that the face image belongs to multiple different identities with a high success rate. One characteristic of the UAXs crafted with our method is that they are universal (identity-agnostic); they are successful even against identities not known in advance. For a certain deep neural network, we show that we are able to spoof almost all tested identities (99\%), including those not known beforehand (not included in training). Our results indicate that a multiple-identity attack is a real threat and should be taken into account when deploying face recognition systems.

📄 PDF Abstract BibTeX arXiv:2110.00708

Code (0)

등록된 구현이 없습니다.

Tasks

Face RecognitionFace Verification

Similar Papers 제목 키워드 기반

AdvFAS: A robust face anti-spoofing framework against adversarial examples

2023-08-04 · Jiawei Chen, Xiao Yang, Heng Yin, Mingzhi Ma 외

Ensuring the reliability of face recognition systems against presentation attacks necessitates the deployment of face anti-spoofing techniques. Despite considerable advancements in this domain, the ability of even the mo…

Adversarial DefenseFace Anti-SpoofingFace Recognition

Malafide: a novel adversarial convolutive noise attack against deepfake and spoofing detection systems

2023-06-13 · Michele Panariello, Wanying Ge, Hemlata Tak, Massimiliano Todisco 외

We present Malafide, a universal adversarial attack against automatic speaker verification (ASV) spoofing countermeasures (CMs). By introducing convolutional noise using an optimised linear time-invariant filter, Malafid…

Adversarial AttackFace SwappingSelf-Supervised LearningSpeaker Verification

Principles of Designing Robust Remote Face Anti-Spoofing Systems

2024-06-06 · Xiang Xu, Tianchen Zhao, Zheng Zhang, Zhihua Li 외

Protecting digital identities of human face from various attack vectors is paramount, and face anti-spoofing plays a crucial role in this endeavor. Current approaches primarily focus on detecting spoofing attempts within…

Face Anti-SpoofingFace Swapping

Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Models

2024-05-27 · Fengfan Zhou, Qianyu Zhou, Hefei Ling, Xuequan Lu

Adversarial attacks on Face Recognition (FR) systems have demonstrated significant effectiveness against standalone FR models. However, their practicality diminishes in complete FR systems that incorporate Face Anti-Spoo…

Face Anti-SpoofingFace Recognition

Domain-generalizable Face Anti-Spoofing with Patch-based Multi-tasking and Artifact Pattern Conversion

2026-04-10 · Seungjin Jung, Yonghyun Jeong, Minha Kim, Jimin Min 외 arxiv

Face Anti-Spoofing (FAS) algorithms, designed to secure face recognition systems against spoofing, struggle with limited dataset diversity, impairing their ability to handle unseen visual domains and spoofing methods. We…

Domain GeneralizationMulti-Task LearningFace Anti-SpoofingFace Recognition