activity
20242026
collaborators

6 papers

cs.CV2026

FairForensics: Seeing Expressions and Parsing Demographics via Vision-Language Modeling for Generalizable Fair Deepfake Detection

Yaning Zhang, Jiao Wu, Zan Gao +1

The challenge of fair deepfake detection (FDD) has attracted increasing attention. Existing fairness-enhanced detectors often suffer from suboptimal generalization to unseen manipu…

cs.CV2026

PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution

Yaning Zhang, Jiahe Zhang, Chunjie Ma +3

The challenge of tracing the source attribution of forged faces has gained significant attention due to the rapid advancement of generative models. However, existing deepfake attri…

cs.CV2026

MFVLR: Multi-domain Fine-grained Vision-Language Reconstruction for Generalizable Diffusion Face Forgery Detection and Localization

Yaning Zhang, Tianyi Wang, Zan Gao +3

The swift advancement in photo-realistic face generation technology has sparked considerable concerns across society and academia, emphasizing the requirement of generalizable face…

cs.CV2026

GazeCLIP: Gaze-Guided CLIP with Adaptive-Enhanced Fine-Grained Language Prompt for Deepfake Attribution and Detection

Yaning Zhang, Linlin Shen, Zitong Yu +2

Current deepfake attribution or deepfake detection works tend to exhibit poor generalization to novel generative methods due to the limited exploration in visual modalities alone.…

cs.CV2025

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

Yaning Zhang, Tianyi Wang, Zitong Yu +3

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable…

cs.CV2024

Distilled Transformers with Locally Enhanced Global Representations for Face Forgery Detection

Yaning Zhang, Qiufu Li, Zitong Yu +1

Face forgery detection (FFD) is devoted to detecting the authenticity of face images. Although current CNN-based works achieve outstanding performance in FFD, they are susceptible…