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

Deep Neural Networks (DNNs) for 3D point cloud recognition are vulnerable toadversarial examples, threatening their practical deployment. Despite the manyresearch endeavors have been made to tackle this issue in recent years, thediversity of adversarial examples on 3D point clouds makes them morechallenging to defend against than those on 2D images. For examples, attackerscan generate adversarial examples by adding, shifting, or removing points.Consequently, existing defense strategies are hard to counter unseen pointcloud adversarial examples. In this paper, we first establish a comprehensive,and rigorous point cloud adversarial robustness benchmark to evaluateadversarial robustness, which can provide a detailed understanding of theeffects of the defense and attack methods. We then collect existing defensetricks in point cloud adversarial defenses and then perform extensive andsystematic experiments to identify an effective combination of these tricks.Furthermore, we propose a hybrid training augmentation methods that considervarious types of point cloud adversarial examples to adversarial training,significantly improving the adversarial robustness. By combining these tricks,we construct a more robust defense framework achieving an average accuracy of83.45\% against various attacks, demonstrating its capability to enablingrobust learners. Our codebase are open-sourced on:\url{https://github.com/qiufan319/benchmark_pc_attack.git}.

Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples