collaborators

7 papers

cs.CV2026

Detecting Deepfakes via Hamiltonian Dynamics

Harry Cheng, Ming-Hui Liu, Tianyi Wang +3

Driven by the rapid development of generative AI models, deepfake detectors are compelled to undergo periodic recalibration to capture newly developed synthetic artifacts. To break…

cs.CV2026

Towards Generalizable Deepfake Detection via Real Distribution Bias Correction

Ming-Hui Liu, Harry Cheng, Xin Luo +2

To generalize deepfake detectors to future unseen forgeries, most existing methods attempt to simulate the dynamically evolving forgery types using available source domain data. Ho…

cs.CV2025

FractalForensics: Proactive Deepfake Detection and Localization via Fractal Watermarks

Tianyi Wang, Harry Cheng, Ming-Hui Liu +1

Proactive Deepfake detection via robust watermarks has seen interest ever since passive Deepfake detectors encountered challenges in identifying high-quality synthetic images. Howe…

cs.CV2025

Suppressing Gradient Conflict for Generalizable Deepfake Detection

Ming-Hui Liu, Harry Cheng, Xin Luo +1

Robust deepfake detection models must be capable of generalizing to ever-evolving manipulation techniques beyond training data. A promising strategy is to augment the training data…

cs.LG2025

Fair Deepfake Detectors Can Generalize

Harry Cheng, Ming-Hui Liu, Yangyang Guo +3

Deepfake detection models face two critical challenges: generalization to unseen manipulations and demographic fairness among population groups. However, existing approaches often…

cs.CV2025

Learning Real Facial Concepts for Independent Deepfake Detection

Ming-Hui Liu, Harry Cheng, Tianyi Wang +2

Deepfake detection models often struggle with generalization to unseen datasets, manifesting as misclassifying real instances as fake in target domains. This is primarily due to an…