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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In recent years, DeepFake is becoming a common threat to our society, due tothe remarkable progress of generative adversarial networks (GAN) in imagesynthesis. Unfortunately, existing studies that propose various approaches, infighting against DeepFake and determining if the facial image is real or fake,is still at an early stage. Obviously, the current DeepFake detection methodstruggles to catch the rapid progress of GANs, especially in the adversarialscenarios where attackers can evade the detection intentionally, such as addingperturbations to fool the DNN-based detectors. While passive detection simplytells whether the image is fake or real, DeepFake provenance, on the otherhand, provides clues for tracking the sources in DeepFake forensics. Thus, thetracked fake images could be blocked immediately by administrators and avoidfurther spread in social networks.  In this paper, we investigate the potentials of image tagging in serving theDeepFake provenance tracking. Specifically, we devise a deep learning-basedapproach, named FakeTagger, with a simple yet effective encoder and decoderdesign along with channel coding to embed message to the facial image, which isto recover the embedded message after various drastic GAN-based DeepFaketransformation with high confidence. The embedded message could be employed torepresent the identity of facial images, which further contributed to DeepFakedetection and provenance. Experimental results demonstrate that our proposedapproach could recover the embedded message with an average accuracy of morethan 95% over the four common types of DeepFakes. Our research finding confirmseffective privacy-preserving techniques for protecting personal photos frombeing DeepFaked.

FakeTagger: Robust Safeguards against DeepFake Dissemination via Provenance Tracking