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

Recent years have seen a surge in the popularity of acoustics-enabledpersonal devices powered by machine learning. Yet, machine learning has provento be vulnerable to adversarial examples. A large number of modern systemsprotect themselves against such attacks by targeting artificiality, i.e., theydeploy mechanisms to detect the lack of human involvement in generating theadversarial examples. However, these defenses implicitly assume that humans areincapable of producing meaningful and targeted adversarial examples. In thispaper, we show that this base assumption is wrong. In particular, wedemonstrate that for tasks like speaker identification, a human is capable ofproducing analog adversarial examples directly with little cost andsupervision: by simply speaking through a tube, an adversary reliablyimpersonates other speakers in eyes of ML models for speaker identification.Our findings extend to a range of other acoustic-biometric tasks such asliveness detection, bringing into question their use in security-criticalsettings in real life, such as phone banking.

Tubes Among Us: Analog Attack on Automatic Speaker Identification