Research map / Adversarial robustness and security / Certified and empirical robustness
On the Need for Topology-Aware Generative Models for Manifold-Based Defenses
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Train the generative model with class-wise topology information instead of using class-ignorant training | Real NVP-based INC · Two-moons | projection error: 0.647 (0.666) -> 0.148 (0.208) | Helped |
| Train the generative model with class-wise topology information instead of using class-ignorant training | Real NVP-based INC · Spirals | projection error: 1.523 (1.338) -> 0.443 (0.440) | Helped |
| Train the generative model with class-wise topology information instead of using class-ignorant training | Real NVP-based INC · Circles | projection error: 0.699 (0.491) -> 0.180 (0.259) | Helped |
Closest papers by meaning
- Adversarial Purification with the Manifold Hypothesis (AAAI 2024 · similarity 0.88)
- Enhancing the Adversarial Robustness via Manifold Projection (AAAI 2025 · similarity 0.87)
- Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution (ICML 2024 · similarity 0.85)
- When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning (AAAI 2025 · similarity 0.85)
- What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models (ICLR 2025 · similarity 0.85)
- Generative Model Inversion Through the Lens of the Manifold Hypothesis (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.