Iris Presentation Attack Detection on Iris PAD Open-set (test) benchmark leaderboard · SOTA2 Research

Iris Presentation Attack Detection on Iris PAD Open-set (test)

-0.0523Performance Score (Printout)DINOv2 + SVM-Linear

Evaluation Results

Method	Links
DINOv2 + SVM-Linear2026.03		-0.0523	-0.1247	-0.0033	-0.0613	0.0017	-0.0351	0.1737	-0.0145
DINOv2 + LogReg2026.03		-0.0326	-0.1079	0.0378	-0.034	0.0086	-0.0327	0.152	-0.0013
High Entropy2026.03		-0.0184	0.052	0.0073	-0.0712	-0.0123	-0.005	0.0175	-0.0043
DINOv2 + SVM-RBF2026.03		-0.0104	0.0023	0.1796	0.1121	-0.0159	-0.0448	0.1167	0.0485
Equal Entropy2026.03		-0.001	0.0847	-0.0098	-0.0122	-0.0021	0.0274	0.0277	0.0164
Low Entropy2026.03		-0.0001	-0.0077	0.0294	-0.016	-0.0384	0.014	-0.0157	-0.0049
Baseline Saliency-based2026.03		0.0087	-0.0052	0.0385	-0.0511	-0.0212	0.0345	0.0232	0.0039
Full Eye Tracking2026.03		0.0473	0.0282	-0.0468	0.0941	-0.0155	0.0474	0.2387	0.0562
Initial Eye Tracking2026.03		0.0513	0.0192	-0.0155	0.0236	-0.0481	0.065	0.2672	0.0518
De-noised Full ET2026.03		0.0604	0.0345	-0.082	0.0621	-0.0782	0.0597	0.2438	0.0429
De-noised Initial ET2026.03		0.0627	0.0574	-0.0645	0.109	-0.0453	0.0372	0.2692	0.0608
DenseNet (XENT)2026.03		0.9169	0.6537	0.8012	0.6541	0.9717	0.745	0.655	0.7711