Certifying Robustness via Topological Representations

📝 Original Info

• Title: Certifying Robustness via Topological Representations
• ArXiv ID: 2501.10876
• Date: 2025-01-18
• Authors: ** 제공된 정보에 저자 명단이 포함되어 있지 않습니다. (논문 원문이나 DOI를 확인해 주세요.) **

📝 Abstract

We propose a neural network architecture that can learn discriminative geometric representations of data from persistence diagrams, common descriptors of Topological Data Analysis. The learned representations enjoy Lipschitz stability with a controllable Lipschitz constant. In adversarial learning, this stability can be used to certify $ε$-robustness for samples in a dataset, which we demonstrate on the ORBIT5K dataset representing the orbits of a discrete dynamical system.

💡 Deep Analysis

📄 Full Content

Reference