cs.CVNov 5, 2026

VIPA: View-Invariant Projector-Based Adversarial Attack

Authors: Jiyu Han, Qingyue Deng, Bingyao Huang

Organizations: Southwest University

Abstract

Projector-based adversarial attack aims to physically manipulate real-world scenes by projecting adversarial patterns, thereby causing deep image classifiers to produce incorrect predictions. However, existing stealthy projector-based adversarial attack methods model the project-and-capture process in a single and static view, limiting their view-invariant capability and practical applicability in dynamic environments. In this paper, we introduce View-Invariant Projector-Based Adversarial Attack (VIPA), a novel method designed to overcome these limitations by achieving both view-invariant and classifier-agnostic adversarial attacks in the physical world. We first leverage a view-invariant projector-camera system simulation method to model the physical interactions between projected patterns and real-world surfaces. To ensure robustness and stealthiness of the attack across different views, VIPA optimizes adversarial projections by aggregating simulated attack losses from multiple views. This joint optimization across diverse views helps maintain robustness regardless of the viewpoints. Finally, the optimized patterns are physically projected into real-world scenes, where they successfully fool various classifiers from different viewpoints, thereby enabling robust and practical view-invariant adversarial attacks. Our experiments in both targeted and untargeted attacks demonstrate that VIPA consistently achieves higher attack success rates than existing methods, while also enhancing stealthiness and ensuring minimal perceptual degradation across all tested views.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples

    Aug 15, 2026Kaisheng Liang, Yiming Cao, Bin XiaoAdversarial AttacksTransfer-Based Adversarial Attacks

  2. VFACamou: View-Fused Adversarial Camouflage for Environment-Adaptive Physical Evasion

    Jun 18, 2026Shihui Yan, Hu Liu, Junyu Shi +6Adversarial AttacksAdversarial Attacks on Object Detectors

  3. Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer

    Aug 21, 2026Qi Song, Ziyuan Luo, Haoliang Han +1Adversarial AttacksAdversarial Perturbations