Transferable 3D Adversarial Textures using End-to-end Optimization

Camilo Pestana Cardeno, Naveed Akhtar, Nazanin Rahnavard, Mubarak Shah, Ajmal Mian

Research output: Chapter in Book/Conference paperConference paperpeer-review

Abstract

Deep visual models are known to be vulnerable to adversarial attacks. The last few years have seen numerous techniques to compute adversarial inputs for these models. However, there are still under-explored avenues in this critical research direction. Among those is the estimation of adversarial textures for 3D models in an end-to-end optimization scheme. In this paper, we propose such a scheme to generate adversarial textures for 3D models that are highly transferable and invariant to different camera views and lighting conditions. Our method makes use of neural rendering with explicit control over the model texture and background. We ensure transferability of the adversarial textures by employing an ensemble of robust and non-robust models. Our technique utilizes 3D models as a proxy to simulate closer to real-life conditions, in contrast to conventional use of 2D images for adversarial attacks. We show the efficacy of our method with extensive experiments. © 2022 IEEE.
Original languageEnglish
Title of host publicationIEEE/CVF Winter Conference on Applications of Computer Vision
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages727-736
Number of pages10
ISBN (Electronic)9781665409155
DOIs
Publication statusPublished - 2022
Event2022 IEEE Winter Conference on Applications of Computer Vision - Waikoloa, United States
Duration: 4 Jan 20228 Jan 2022

Conference

Conference2022 IEEE Winter Conference on Applications of Computer Vision
Abbreviated titleWACV 2022
Country/TerritoryUnited States
CityWaikoloa
Period4/01/228/01/22

Fingerprint

Dive into the research topics of 'Transferable 3D Adversarial Textures using End-to-end Optimization'. Together they form a unique fingerprint.

Cite this