Abstract | ||
---|---|---|
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 method, 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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/IJCB52358.2021.9484380 | 2021 IEEE International Joint Conference on Biometrics (IJCB) |
Keywords | DocType | ISSN |
deep face recognition systems,universal adversarial spoofing attacks,multiple-identity attack,tested identities,deep neural network,identity-agnostic,face verification system,pixel level,small perturbations,face image,deep feature representation | Conference | 2474-9680 |
ISBN | Citations | PageRank |
978-1-6654-3781-3 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Takuma Amada | 1 | 0 | 0.34 |
Seng Pei Liew | 2 | 0 | 1.35 |
Kazuya Kakizaki | 3 | 0 | 2.37 |
Toshinori Araki | 4 | 59 | 3.62 |