arXiv Computer Vision
Beyond Shortcut Learning: Hierarchical Spatial Prototype Regularization for Face Forgery Detection
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jul 27
Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection
arXiv:2411. 19715v4 Announce Type: replace-cross Abstract: We describe Forensics Adapter, an adapter network designed to transform CLIP into an effective and generalizable face forgery detector.
arXiv Computer Vision
Oct 7
Forensic Reserve: Eliciting Latent Knowledge for Image Forgery Detection
arXiv:2610.08639v1 Announce Type: new Abstract: As generated images become increasingly realistic, reliable forgery detection is essential for maintaining trust in visual information. However, existi...
arXiv AI
Aug 10
Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection
arXiv:2608. 06865v1 Announce Type: cross Abstract: The malicious use of generative artificial intelligence to create highly realistic deepfake videos raises serious ethical concerns and poses substantial challenges to AI safety.
arXiv AI
Jun 2
Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
arXiv:2606. 01843v1 Announce Type: cross Abstract: Deepfake detection suffers from poor generalization across forgery methods, as existing models tend to rely on spurious method-specific shortcuts that fail to transfer to unseen manipulations.
arXiv AI
Sep 18
FORGE: Forensic Reasoning with Grounded Evidence
FORGE is a forensic deepfake analysis system that provides region‑grounded natural language explanations for image manipulations. It addresses the inductive bias mismatch of multimodal large language models by adding a Vision‑Only Model trained on dense patch prediction, allowing the language model to interleave tokens with preserved spatial correspondence. Across face‑manipulated and fully synthetic content, FORGE delivers fine‑grained attribute queries and outperforms in‑domain baselines, with region‑specific evaluation and human studies confirming explanation faithfulness.
arXiv Computer Vision
Oct 2
Revisiting Cross-Reconstruction for Generalizable Deepfake Detection
arXiv:2610.01544v1 Announce Type: new Abstract: Existing image forgery detectors often suffer from generalization to unseen manipulation methods due to the limited ability to capture transferable for...