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

Recently, generative adversarial networks (GANs) can generate photo-realisticfake facial images which are perceptually indistinguishable from real facephotos, promoting research on fake face detection. Though fake face forensicscan achieve high detection accuracy, their anti-forensic counterparts are lessinvestigated. Here we explore more \textit{imperceptible} and\textit{transferable} anti-forensics for fake face imagery detection based onadversarial attacks. Since facial and background regions are often smooth, evensmall perturbation could cause noticeable perceptual impairment in fake faceimages. Therefore it makes existing adversarial attacks ineffective as ananti-forensic method. Our perturbation analysis reveals the intuitive reason ofthe perceptual degradation issue when directly applying existing attacks. Wethen propose a novel adversarial attack method, better suitable for imageanti-forensics, in the transformed color domain by considering visualperception. Simple yet effective, the proposed method can fool both deeplearning and non-deep learning based forensic detectors, achieving higherattack success rate and significantly improved visual quality. Specially, whenadversaries consider imperceptibility as a constraint, the proposedanti-forensic method can improve the average attack success rate by around 30\%on fake face images over two baseline attacks. \textit{More imperceptible} and\textit{more transferable}, the proposed method raises new security concerns tofake face imagery detection. We have released our code for public use, andhopefully the proposed method can be further explored in related forensicapplications as an anti-forensic benchmark.

Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery Detection