3 papers
cs.CV2026
DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection
Jiazhen Yan, Ziqiang Li, Fan Wang +3
The rapid progress of generative models such as GANs and diffusion models has led to the widespread proliferation of AI-generated images, raising concerns about misinformation, pri…
cs.CV2026
Breaking the Resolution Barrier: Arbitrary-resolution Deep Image Steganography Framework
Xinjue Hu, Chi Wang, Boyu Wang +3
Deep image steganography (DIS) has achieved significant results in capacity and invisibility. However, current paradigms enforce the secret image to maintain the same resolution as…
cs.CV2026
Low-rank Orthogonal Subspace Intervention for Generalizable Face Forgery Detection
Chi Wang, Xinjue Hu, Boyu Wang +2
The generalization problem remains a key challenge in face forgery detection. This paper explores the reasons for the generalization failure of Vanilla CLIP: in ``real vs. fake" de…