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

The modern open internet contains billions of public images of human facesacross the web, especially on social media websites used by half the world'spopulation. In this context, Face Recognition (FR) systems have the potentialto match faces to specific names and identities, creating glaring privacyconcerns. Adversarial attacks are a promising way to grant users privacy fromFR systems by disrupting their capability to recognize faces. Yet, such attackscan be perceptible to human observers, especially under the more challengingblack-box threat model. In the literature, the justification for theimperceptibility of such attacks hinges on bounding metrics such as $\ell_p$norms. However, there is not much research on how these norms match up withhuman perception. Through examining and measuring both the effectiveness ofrecent black-box attacks in the face recognition setting and theircorresponding human perceptibility through survey data, we demonstrate thetrade-offs in perceptibility that occur as attacks become more aggressive. Wealso show how the $\ell_2$ norm and other metrics do not correlate with humanperceptibility in a linear fashion, thus making these norms suboptimal atmeasuring adversarial attack perceptibility.

Examining the Human Perceptibility of Black-Box Adversarial Attacks on Face Recognition