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

Investigating new methods of creating face morphing attacks is essential toforesee novel attacks and help mitigate them. Creating morphing attacks iscommonly either performed on the image-level or on the representation-level.The representation-level morphing has been performed so far based on generativeadversarial networks (GAN) where the encoded images are interpolated in thelatent space to produce a morphed image based on the interpolated vector. Sucha process was constrained by the limited reconstruction fidelity of GANarchitectures. Recent advances in the diffusion autoencoder models haveovercome the GAN limitations, leading to high reconstruction fidelity. Thistheoretically makes them a perfect candidate to perform representation-levelface morphing. This work investigates using diffusion autoencoders to createface morphing attacks by comparing them to a wide range of image-level andrepresentation-level morphs. Our vulnerability analyses on fourstate-of-the-art face recognition models have shown that such models are highlyvulnerable to the created attacks, the MorDIFF, especially when compared toexisting representation-level morphs. Detailed detectability analyses are alsoperformed on the MorDIFF, showing that they are as challenging to detect asother morphing attacks created on the image- or representation-level. Data andmorphing script are made public: https://github.com/naserdamer/MorDIFF.

MorDIFF: Recognition Vulnerability and Attack Detectability of Face Morphing Attacks Created by Diffusion Autoencoders