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

Computer vision applications like automated face detection are used for avariety of purposes ranging from unlocking smart devices to tracking potentialpersons of interest for surveillance. Audits of these applications haverevealed that they tend to be biased against minority groups which result inunfair and concerning societal and political outcomes. Despite multiple studiesover time, these biases have not been mitigated completely and have in factincreased for certain tasks like age prediction. While such systems are auditedover benchmark datasets, it becomes necessary to evaluate their robustness foradversarial inputs. In this work, we perform an extensive adversarial audit onmultiple systems and datasets, making a number of concerning observations -there has been a drop in accuracy for some tasks on CELEBSET dataset since aprevious audit. While there still exists a bias in accuracy against individualsfrom minority groups for multiple datasets, a more worrying observation is thatthese biases tend to get exorbitantly pronounced with adversarial inputs towardthe minority group. We conclude with a discussion on the broader societalimpacts in light of these observations and a few suggestions on how tocollectively deal with this issue.

Two-Face: Adversarial Audit of Commercial Face Recognition Systems