Research map / Adversarial robustness and security / Certified and empirical robustness
A Spectral View of Adversarially Robust Features
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 |
|---|---|---|---|
| use weighted-edge graph instead of thresholded unweighted graph for spectral features (ablation) | spectral features + linear classifier · MNIST adversarial images | accuracy under transfer attack | Helped |
| replace PGD-trained neural net with weighted-laplacian spectral features + linear classifier | MNIST classifier · MNIST adversarial images, large perturbations | accuracy under transfer attack | Mixed |
Closest papers by meaning
- Adversarially Robust Generalization Requires More Data (NeurIPS 2018 · similarity 0.90)
- Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization (NeurIPS 2022 · similarity 0.90)
- SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation (ICML 2021 · similarity 0.90)
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 2025 · similarity 0.89)
- Learning Better Certified Models from Empirically-Robust Teachers (NeurIPS 2026 · similarity 0.88)
- Robust Feature Learning for Multi-Index Models in High Dimensions (ICLR 2025 · similarity 0.88)
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.