Adversarial Attacks on Hyperbolic Networks

2024/12/02 by Max van Spengler, van Spengler, Max, Jan Zahálka +3 · 1 citation
Social Sciences · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Terrorism, Counterterrorism, and Political Violence

paper · pdf · doi:10.48550/arxiv.2412.01495

openalex publication_date 2024/12/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

As hyperbolic deep learning grows in popularity, so does the need for adversarial robustness in the context of such a non-Euclidean geometry. To this end, this paper proposes hyperbolic alternatives to the commonly used FGM and PGD adversarial attacks. Through interpretable synthetic benchmarks and experiments on existing datasets, we show how the existing and newly proposed attacks differ. Moreover, we investigate the differences in adversarial robustness between Euclidean and fully hyperbolic networks. We find that these networks suffer from different types of vulnerabilities and that the newly proposed hyperbolic attacks cannot address these differences. Therefore, we conclude that the shifts in adversarial robustness are due to the models learning distinct patterns resulting from their different geometries.

Cited by

• Geometry-Aware Backdoor Attacks: Leveraging Curvature in Hyperbolic Embeddings

Related

• Angular Gradient Sign Method: Uncovering Vulnerabilities in Hyperbolic Networks
• Robustness of Rotation-Equivariant Networks to Adversarial Perturbations
• Adversarial attacks on neural networks through canonical Riemannian foliations
• Autoencoding Hyperbolic Representation for Adversarial Generation
• A Geometric Framework for Adversarial Vulnerability in Machine Learning