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

Automatic speech recognition (ASR) models are prevalent, particularly inapplications for voice navigation and voice control of domestic appliances. Thecomputational core of ASRs are deep neural networks (DNNs) that have been shownto be susceptible to adversarial perturbations; easily misused by attackers togenerate malicious outputs. To help test the security and robustnesss of ASRS,we propose techniques that generate blackbox (agnostic to the DNN), untargetedadversarial attacks that are portable across ASRs. This is in contrast toexisting work that focuses on whitebox targeted attacks that are time consumingand lack portability.  Our techniques generate adversarial attacks that have no human audibledifference by manipulating the audio signal using a psychoacoustic model thatmaintains the audio perturbations below the thresholds of human perception. Weevaluate portability and effectiveness of our techniques using three popularASRs and two input audio datasets using the metrics - Word Error Rate (WER) ofoutput transcription, Similarity to original audio, attack Success Rate ondifferent ASRs and Detection score by a defense system. We found ouradversarial attacks were portable across ASRs, not easily detected by astate-of-the-art defense system, and had significant difference in outputtranscriptions while sounding similar to original audio.

Catch Me If You Can: Blackbox Adversarial Attacks on Automatic Speech Recognition using Frequency Masking