arXiv AI
Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 26
Spectra: Multi-Scale Implicit Decomposition for Deepfake Detection
Spectra is a deepfake detection framework that uses implicit neural representations (INRs) to analyze how an image is reconstructed, producing multi-level reconstruction heatmaps. These heatmaps are fused with semantic visual features via a bidirectional mechanism, enabling the model to detect forgery cues that are less tied to specific generation pipelines. Experiments on several deepfake benchmarks show that Spectra outperforms detectors relying only on RGB appearance or semantic representations, and it also extends to face presentation attack detection.
arXiv AI
Aug 17
Redefining Generalization in Visual Domains: A Two-Axis Framework for Fake Image Detection with FusionDetect
arXiv:2510. 05740v2 Announce Type: replace-cross Abstract: The rapid development of generative models has made it increasingly crucial to develop detectors that can reliably detect synthetic images.
arXiv Computer Vision
Sep 16
Unifying Semantic Priors and High-Frequency Traces: Enhancing V-JEPA with Mixture-of-Experts for Robust Synthetic Image Forensics
The paper introduces MoE-JEPA, a dual‑stream deepfake detection model that combines a V‑JEPA backbone with a Residual Mixture‑of‑Experts mechanism and a noise stream branch. It further incorporates a Gated Attention Multiple Instance Learning module to refine spatial semantic understanding. On the SID‑Set benchmark, MoE‑JEPA achieves a new state‑of‑the‑art accuracy of 95.54%, outperforming much larger models.
arXiv Computer Vision
Oct 21
Only Train Once: Uncertainty-Aware One-Class Learning for Face Authenticity Detection
The paper introduces FADNet, a face authenticity detector that treats forgery detection as a one‑class classification problem, training only on authentic faces. It uses Evidential Deep Learning to measure uncertainty and a pseudo‑forgery generator to sharpen decision boundaries. Experiments on DF40 and ASFD show FADNet surpasses state‑of‑the‑art methods with 96.63% accuracy and 98.83% precision.
arXiv AI
Oct 16
DINO-FIL: Multi-Layer Transformer Fusion for Generative Inpainting Forgery Localization
DINO-FIL is a transformer-based framework that localizes generative image forgeries at the pixel level. It fuses multi‑layer representations from a pretrained DINOv3 ViT‑H+/16 encoder with a lightweight decoder to detect both semantic and fine‑grained texture inconsistencies. In cross‑dataset experiments, DINO‑FIL outperforms existing baselines on most datasets while preserving a high true‑negative rate for pristine images.
arXiv AI
Jun 2
CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection
arXiv:2606. 00101v1 Announce Type: cross Abstract: With the rapid advancement of artificial intelligence generated content (AIGC) technologies, video forgery has become increasingly prevalent, posing new challenges to public discourse and societal security.