3 papers
cs.CV2026
Emergent Region-Level Facial Correspondence in Frozen Vision Foundation Models
Izaldein Al-Zyoud, Abdulmotaleb El Saddik
Frozen self-supervised vision models can align parts of generic objects, but it remains unclear whether this correspondence extends to human faces, where global layout is shared wh…
cs.CV2026
Segmentation-Guided Spatial Indexing for Generalizable and Explainable Deepfake Detection
Izaldein Al-Zyoud, Abdulmotaleb El Saddik
We introduce segmentation-guided spatial indexing for generalizable and explainable deepfake detection. The key idea reverses the standard design order: rather than pooling all fac…
eess.IV2026
Rethinking Feature Conditioning for Robust Forged Media Detection in Edge AI Sensing Systems
Izaldein Al-Zyoud, Abdulmotaleb El Saddik
Generalization under manipulation and dataset shift remains a core challenge in forged media detection for AI-driven edge sensing systems. Frozen vision foundation models with line…