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

Generalizable Neural Radiance Fields (GNeRF) are one of the most promisingreal-world solutions for novel view synthesis, thanks to their cross-scenegeneralization capability and thus the possibility of instant rendering on newscenes. While adversarial robustness is essential for real-world applications,little study has been devoted to understanding its implication on GNeRF. Wehypothesize that because GNeRF is implemented by conditioning on the sourceviews from new scenes, which are often acquired from the Internet orthird-party providers, there are potential new security concerns regarding itsreal-world applications. Meanwhile, existing understanding and solutions forneural networks' adversarial robustness may not be applicable to GNeRF, due toits 3D nature and uniquely diverse operations. To this end, we present NeRFool,which to the best of our knowledge is the first work that sets out tounderstand the adversarial robustness of GNeRF. Specifically, NeRFool unveilsthe vulnerability patterns and important insights regarding GNeRF's adversarialrobustness. Built upon the above insights gained from NeRFool, we furtherdevelop NeRFool+, which integrates two techniques capable of effectivelyattacking GNeRF across a wide range of target views, and provide guidelines fordefending against our proposed attacks. We believe that our NeRFool/NeRFool+lays the initial foundation for future innovations in developing robustreal-world GNeRF solutions. Our codes are available at:https://github.com/GATECH-EIC/NeRFool.

NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations