GenD achieves state-of-the-art average cross-dataset AUROC in deepfake detection by parameter-efficient adaptation of a foundational vision encoder with hyperspherical manifold enforcement via L2 normalization and metric learning.
Advancing high fidelity identity swapping for forgery detection
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3representative citing papers
A multi-stream ensemble using DINOv2 and CLIP backbones trained with extreme degradations achieves stable deepfake detection and fourth place in the NTIRE 2026 challenge.
The NTIRE 2026 challenge finds that large foundation models combined with ensembles and degradation-aware training produce the most robust deepfake detectors.
citing papers explorer
-
Deepfake Detection that Generalizes Across Benchmarks
GenD achieves state-of-the-art average cross-dataset AUROC in deepfake detection by parameter-efficient adaptation of a foundational vision encoder with hyperspherical manifold enforcement via L2 normalization and metric learning.
-
Robust Deepfake Detection: Mitigating Spatial Attention Drift via Calibrated Complementary Ensembles
A multi-stream ensemble using DINOv2 and CLIP backbones trained with extreme degradations achieves stable deepfake detection and fourth place in the NTIRE 2026 challenge.
-
Robust Deepfake Detection, NTIRE 2026 Challenge: Report
The NTIRE 2026 challenge finds that large foundation models combined with ensembles and degradation-aware training produce the most robust deepfake detectors.