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

With the proliferation of face image manipulation (FIM) techniques such asFace2Face and Deepfake, more fake face images are spreading over the internet,which brings serious challenges to public confidence. Face image forgerydetection has made considerable progresses in exposing specific FIM, but it isstill in scarcity of a robust fake face detector to expose face image forgeriesunder complex scenarios such as with further compression, blurring, scaling,etc. Due to the relatively fixed structure, convolutional neural network (CNN)tends to learn image content representations. However, CNN should learn subtlemanipulation traces for image forensics tasks. Thus, we propose an adaptivemanipulation traces extraction network (AMTEN), which serves as pre-processingto suppress image content and highlight manipulation traces. AMTEN exploits anadaptive convolution layer to predict manipulation traces in the image, whichare reused in subsequent layers to maximize manipulation artifacts by updatingweights during the back-propagation pass. A fake face detector, namelyAMTENnet, is constructed by integrating AMTEN with CNN. Experimental resultsprove that the proposed AMTEN achieves desirable pre-processing. When detectingfake face images generated by various FIM techniques, AMTENnet achieves anaverage accuracy up to 98.52%, which outperforms the state-of-the-art works.When detecting face images with unknown post-processing operations, thedetector also achieves an average accuracy of 95.17%.

Fake face detection via adaptive manipulation traces extraction network