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

The success of multimodal data fusion in deep learning appears to beattributed to the use of complementary in-formation between multiple inputdata. Compared to their predictive performance, relatively less attention hasbeen devoted to the robustness of multimodal fusion models. In this paper, weinvestigated whether the current multimodal fusion model utilizes thecomplementary intelligence to defend against adversarial attacks. We appliedgradient based white-box attacks such as FGSM and PGD on MFNet, which is amajor multispectral (RGB, Thermal) fusion deep learning model for semanticsegmentation. We verified that the multimodal fusion model optimized for betterprediction is still vulnerable to adversarial attack, even if only one of thesensors is attacked. Thus, it is hard to say that existing multimodal datafusion models are fully utilizing complementary relationships between multiplemodalities in terms of adversarial robustness. We believe that our observationsopen a new horizon for adversarial attack research on multimodal data fusion.

Investigating Vulnerability to Adversarial Examples on Multimodal Data Fusion in Deep Learning