Targeted View-Invariant Adversarial Perturbations for 3D Object Recognition

Autor:	Green, Christian, Ergezer, Mehmet, Zeybey, Abdurrahman
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Cryptography and Security Electrical Engineering and Systems Science - Image and Video Processing
Druh dokumentu:	Working Paper
Popis:	Adversarial attacks pose significant challenges in 3D object recognition, especially in scenarios involving multi-view analysis where objects can be observed from varying angles. This paper introduces View-Invariant Adversarial Perturbations (VIAP), a novel method for crafting robust adversarial examples that remain effective across multiple viewpoints. Unlike traditional methods, VIAP enables targeted attacks capable of manipulating recognition systems to classify objects as specific, pre-determined labels, all while using a single universal perturbation. Leveraging a dataset of 1,210 images across 121 diverse rendered 3D objects, we demonstrate the effectiveness of VIAP in both targeted and untargeted settings. Our untargeted perturbations successfully generate a singular adversarial noise robust to 3D transformations, while targeted attacks achieve exceptional results, with top-1 accuracies exceeding 95% across various epsilon values. These findings highlight VIAPs potential for real-world applications, such as testing the robustness of 3D recognition systems. The proposed method sets a new benchmark for view-invariant adversarial robustness, advancing the field of adversarial machine learning for 3D object recognition. Comment: Accepted to AAAI-25 Workshop on Artificial Intelligence for Cyber Security (AICS): http://aics.site/AICS2025/index.html
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2412.13376 Zobrazit plný text záznamu View this record from Arxiv