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/

Zendy Plus

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

Zendy Tools

Zendy Open

Fooling deep neural networks with adversarial input have exposed asignificant vulnerability in the current state-of-the-art systems in multipledomains. Both black-box and white-box approaches have been used to eitherreplicate the model itself or to craft examples which cause the model to fail.In this work, we propose a framework which uses multi-objective evolutionaryoptimization to perform both targeted and un-targeted black-box attacks onAutomatic Speech Recognition (ASR) systems. We apply this framework on two ASRsystems: Deepspeech and Kaldi-ASR, which increases the Word Error Rates (WER)of these systems by upto 980%, indicating the potency of our approach. Duringboth un-targeted and targeted attacks, the adversarial samples maintain a highacoustic similarity of 0.98 and 0.97 with the original audio.

Adversarial Black-Box Attacks on Automatic Speech Recognition Systems using Multi-Objective Evolutionary Optimization