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

DeepFake is becoming a real risk to society and brings potential threats toboth individual privacy and political security due to the DeepFaked multimediaare realistic and convincing. However, the popular DeepFake passive detectionis an ex-post forensics countermeasure and failed in blocking thedisinformation spreading in advance. To address this limitation, researchersstudy the proactive defense techniques by adding adversarial noises into thesource data to disrupt the DeepFake manipulation. However, the existing studieson proactive DeepFake defense via injecting adversarial noises are not robust,which could be easily bypassed by employing simple image reconstructionrevealed in a recent study MagDR.  In this paper, we investigate the vulnerability of the existing forgerytechniques and propose a novel \emph{anti-forgery} technique that helps usersprotect the shared facial images from attackers who are capable of applying thepopular forgery techniques. Our proposed method generates perceptual-awareperturbations in an incessant manner which is vastly different from the priorstudies by adding adversarial noises that is sparse. Experimental resultsreveal that our perceptual-aware perturbations are robust to diverse imagetransformations, especially the competitive evasion technique, MagDR via imagereconstruction. Our findings potentially open up a new research directiontowards thorough understanding and investigation of perceptual-awareadversarial attack for protecting facial images against DeepFakes in aproactive and robust manner. We open-source our tool to foster future research.Code is available at https://github.com/AbstractTeen/AntiForgery/.

Anti-Forgery: Towards a Stealthy and Robust DeepFake Disruption Attack via Adversarial Perceptual-aware Perturbations