LAA-X uses multi-task learning with explicit localized artifact attention and blending synthesis to build a deepfake detector that generalizes to high-quality and unseen manipulations after training only on real and pseudo-fake samples.
Self-supervised transformer for deepfake detection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
AMDD achieves 99.7% balanced accuracy and 99.8% AUC on FakeAVCeleb by using cross-modal forensic fingerprint consistency loss to align generator-specific artifacts across modalities while also reporting 95.9% attribution accuracy.
citing papers explorer
-
LAA-X: Unified Localized Artifact Attention for Quality-Agnostic and Generalizable Face Forgery Detection
LAA-X uses multi-task learning with explicit localized artifact attention and blending synthesis to build a deepfake detector that generalizes to high-quality and unseen manipulations after training only on real and pseudo-fake samples.
-
Attribution-Guided Multimodal Deepfake Detection via Cross-Modal Forensic Fingerprints
AMDD achieves 99.7% balanced accuracy and 99.8% AUC on FakeAVCeleb by using cross-modal forensic fingerprint consistency loss to align generator-specific artifacts across modalities while also reporting 95.9% attribution accuracy.