English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The rapid advancement of deepfake technologies raises significant concernsabout the security of face recognition systems. While existing methods leveragethe clues left by deepfake techniques for face forgery detection, malicioususers may intentionally manipulate forged faces to obscure the traces ofdeepfake clues and thereby deceive detection tools. Meanwhile, attainingcross-domain robustness for data-based methods poses a challenge due topotential gaps in the training data, which may not encompass samples from allrelevant domains. Therefore, in this paper, we introduce a solution - aCross-Domain Robust Bias Expansion Network (BENet) - designed to enhance faceforgery detection. BENet employs an auto-encoder to reconstruct input faces,maintaining the invariance of real faces while selectively enhancing thedifference between reconstructed fake faces and their original counterparts.This enhanced bias forms a robust foundation upon which dependable forgerydetection can be built. To optimize the reconstruction results in BENet, weemploy a bias expansion loss infused with contrastive concepts to attain theaforementioned objective. In addition, to further heighten the amplification offorged clues, BENet incorporates a Latent-Space Attention (LSA) module. ThisLSA module effectively captures variances in latent features between theauto-encoder's encoder and decoder, placing emphasis on inconsistentforgery-related information. Furthermore, BENet incorporates a cross-domaindetector with a threshold to determine whether the sample belongs to a knowndistribution. The correction of classification results through the cross-domaindetector enables BENet to defend against unknown deepfake attacks fromcross-domain. Extensive experiments demonstrate the superiority of BENetcompared with state-of-the-art methods in intra-database and cross-databaseevaluations.

Cross-domain Robust Deepfake Bias Expansion Network for Face Forgery Detection