Video-based Morphing Attack Detection for Improved Security in Operational Scenarios
Video sequences can be leveraged to improve the robustness and performance of morphing attack detection systems compared to traditional single-image or differential image-based approaches.
The Impact of Print-and-Scan on the Effectiveness of Face Morphing Attacks in Heterogeneous Evaluation Scenarios
Print-and-scan processing can significantly increase the effectiveness of face morphing attacks against face recognition systems, regardless of whether the input image is a morphed or bona fide face.
Unreasonably Effective Face Morphing Attacks Using Greedy Diffusion Models
Greedy-DiM, a novel family of face morphing algorithms, achieves unreasonably effective performance in fooling state-of-the-art face recognition systems, outperforming all other morphing attacks compared.
Automated Face Morphing Attacks: Leveraging Deep Embeddings for Efficient Pair Selection and Improved Detection
Leveraging deep face embeddings can significantly improve the attack potential of automated face morphing attacks by enabling efficient selection of morph pairs, while also providing a robust alternative for detecting such attacks.
Face Anti-Spoofing with Test-Time Domain Generalization
A novel Test-Time Domain Generalization (TTDG) framework that leverages testing data to enhance the generalizability of face anti-spoofing models beyond mere evaluation.
© 2024 by Linnk AI