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

Nowadays, machine learning based Automatic Speech Recognition (ASR) techniquehas widely spread in smartphones, home devices, and public facilities. Asconvenient as this technology can be, a considerable security issue also raises-- the users' speech content might be exposed to malicious ASR monitoring andcause severe privacy leakage. In this work, we propose HASP -- ahigh-performance security enhancement approach to solve this security issue onmobile devices. Leveraging ASR systems' vulnerability to the adversarialexamples, HASP is designed to cast human imperceptible adversarial noises toreal-time speech and effectively perturb malicious ASR monitoring by increasingthe Word Error Rate (WER). To enhance the practical performance on mobiledevices, HASP is also optimized for effective adaptation to the human speechcharacteristics, environmental noises, and mobile computation scenarios. Theexperiments show that HASP can achieve optimal real-time security enhancement:it can lead an average WER of 84.55% for perturbing the malicious ASRmonitoring, and the data processing speed is 15x to 40x faster compared to thestate-of-the-art methods. Moreover, HASP can effectively perturb various ASRsystems, demonstrating a strong transferability.

HASP: A High-Performance Adaptive Mobile Security Enhancement Against Malicious Speech Recognition