Unearthing Common Inconsistency for Generalisable Deepfake Detection

no code implementations • 20 Nov 2023 • Beilin Chu, Xuan Xu, Weike You, Linna Zhou

While current image-level detection method fails to generalize to unseen domains, owing to the domain-shift phenomenon brought by CNN's strong inductive bias towards Deepfake texture, video-level one shows its potential to have both generalization across multiple domains and robustness to compression.

Contrastive Learning DeepFake Detection +2

Protecting World Leader Using Facial Speaking Pattern Against Deepfakes

no code implementations • IEEE Signal Processing Letters 2022 • Beilin Chu, Weike You, Zhen Yang, Linna Zhou, Renying Wang

This paper proposes a dual stream learning facial and speaking patterns method to protect celebrities against deepfakes.

DeepFake Detection