Research map / Adversarial robustness and security / Attacks on text and graphs
EyePAD++: A Distillation-Based Approach for Joint Eye Authentication and Presentation Attack Detection Using Periocular Images
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add distillation from a jointly capable EyePAD teacher during MTL training | EyePAD++ versus MTMT · ND-Iris-0405, original, 1 query 1 gallery | OFRR: 0.087 -> 0.072 | Helped |
| Add distillation from a jointly capable EyePAD teacher during MTL training | EyePAD++ versus MTMT · ND-Iris-0405, original, 1 query 5 gallery | OFRR: 0.052 -> 0.043 | Helped |
| Use EyePAD++ instead of MTL | DenseNet121 joint EA and PAD · ND-Iris-0405, blurred, 1 query 5 gallery | OFRR: 0.199 -> 0.192 | Helped |
| Use EyePAD++ instead of MTL | DenseNet121 joint EA and PAD · ND-Iris-0405, noisy, 1 query 5 gallery | OFRR: 0.152 -> 0.082 | Helped |
| Increase the EyePAD feature-distillation weight λ1 (ablation) | EyePAD student · Original ND-Iris-0405 and CU-LivDet | user-to-user verification performance | Helped |
| Increase the EyePAD feature-distillation weight λ1 (ablation) | EyePAD student · Original ND-Iris-0405 and CU-LivDet | PAD performance | Hurt |
| Vary the EyePAD++ distillation weight λ2 (ablation) | EyePAD++ student · Original ND-Iris-0405 and CU-LivDet | EA and PAD performance trend | No clear effect |
Closest papers by meaning
- Multi-Domain Incremental Learning for Face Presentation Attack Detection (AAAI 2024 · similarity 0.82)
- FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models (AAAI 2026 · similarity 0.81)
- FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning (CVPR 2025 · similarity 0.80)
- SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining (AAAI 2025 · similarity 0.80)
- Privacy-Preserving Optics for Enhancing Protection in Face De-Identification (CVPR 2024 · similarity 0.80)
- From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing (CVPR 2026 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.