Deceiving the Protector: Fooling Face Presentation Attack Detection Algorithms
Citations
5 citations
5 citations
5 citations
2 citations
2 citations
References
12,783 citations
9,561 citations
"Deceiving the Protector: Fooling Fa..." refers background in this paper
...[24] observe that small manipulations in the pixel values can lead to its misclassification by deep learning algorithms....
[...]
3,801 citations
"Deceiving the Protector: Fooling Fa..." refers methods in this paper
...On 2D attacks, the SVM with RBF kernel yields the lowest EER value whereas on silicone and digital morph attack linear kernel shows the best performance....
[...]
...%) on digital face morph database increased by more than 14, 10, and 16 times with linear, polynomial, and RBF kernel-based SVM with CNN features, respectively....
[...]
...Similarly, the sensitivity of different SVM kernels is also evaluated against feature tampering....
[...]
...The performance degradation across each SVM kernel on the hand-held set of Replay-Attack database is even higher under inter-attack network training in comparison to intraattack learning....
[...]
...The support vector machine (SVM) [10] classifier is trained for presentation attack detection on CNN features....
[...]
3,533 citations
1,542 citations