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

There are increasing concerns about malicious attacks on autonomous vehicles.In particular, inaudible voice command attacks pose a significant threat asvoice commands become available in autonomous driving systems. How toempirically defend against these inaudible attacks remains an open question.Previous research investigates utilizing deep learning-based multimodal fusionfor defense, without considering the model uncertainty in trustworthiness. Asdeep learning has been applied to increasingly sensitive tasks, uncertaintymeasurement is crucial in helping improve model robustness, especially inmission-critical scenarios. In this paper, we propose the Multimodal FusionFramework (MFF) as an intelligent security system to defend against inaudiblevoice command attacks. MFF fuses heterogeneous audio-vision modalities usingVGG family neural networks and achieves the detection accuracy of 92.25% in thecomparative fusion method empirical study. Additionally, extensive experimentson audio-vision tasks reveal the model's uncertainty. Using ExpectedCalibration Errors, we measure calibration errors and Monte-Carlo Dropout toestimate the predictive distribution for the proposed models. Our findings showempirically to train robust multimodal models, improve standard accuracy andprovide a further step toward interpretability. Finally, we discuss the prosand cons of our approach and its applicability for Advanced Driver AssistanceSystems.

Trustworthy Sensor Fusion against Inaudible Command Attacks in Advanced Driver-Assistance System