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

Adversarial attacks pose serious challenges for deep neural network(DNN)-based analysis of various input signals. In the case of 3D point clouds,methods have been developed to identify points that play a key role in thenetwork decision, and these become crucial in generating existing adversarialattacks. For example, a saliency map approach is a popular method foridentifying adversarial drop points, whose removal would significantly impactthe network decision. Generally, methods for identifying adversarial pointsrely on the deep model itself in order to determine which points are criticallyimportant for the model's decision. This paper aims to provide a novelviewpoint on this problem, in which adversarial points can be predictedindependently of the model. To this end, we define 14 point cloud features anduse multiple linear regression to examine whether these features can be usedfor model-free adversarial point prediction, and which combination of featuresis best suited for this purpose. Experiments show that a suitable combinationof features is able to predict adversarial points of three different networks-- PointNet, PointNet++, and DGCNN -- significantly better than a random guess.The results also provide further insight into DNNs for point cloud analysis, byshowing which features play key roles in their decision-making process.

Model-Free Prediction of Adversarial Drop Points in 3D Point Clouds