Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
DocShield: Towards AI Document Safety via Evidence-Grounded Agentic Reasoning
Fanwei Zeng, Changtao Miao, Jing Huang +8
The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safety. Existing forensic methods mainly re…
cs.CV2025
Towards Generalizable Deepfake Detection with Spatial-Frequency Collaborative Learning and Hierarchical Cross-Modal Fusion
Mengyu Qiao, Runze Tian, Yang Wang
The rapid evolution of deep generative models poses a critical challenge to deepfake detection, as detectors trained on forgery-specific artifacts often suffer significant performa…