Research map / Adversarial robustness and security / Certified and empirical robustness
Robustness of classifiers: from adversarial to random noise
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 |
|---|---|---|---|
| Semi-random subspace dimension reduced from m=d to m=d/100 (perturbation confined to random subspace) | Deep classifiers (LeNet, VGG-F, VGG-19) · MNIST, CIFAR-10, ImageNet | beta(f;m) ratio to sqrt(d/m)*||r*|| | No clear effect |
| Random noise (m=1) vs semi-random subspace with m=10: perceptibility of required perturbation | VGG-F fooling perturbations · ImageNet sample image | qualitative perceptibility | Helped |
Closest papers by meaning
- Robustness of Classifiers to Universal Perturbations: A Geometric Perspective (ICLR 2018 · similarity 0.91)
- Robustness via Curvature Regularization, and Vice Versa (CVPR 2019 · similarity 0.91)
- Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers (NeurIPS 2019 · similarity 0.90)
- Probably Approximately Global Robustness Certification (ICML 2025 · similarity 0.89)
- Compositional Curvature Bounds for Deep Neural Networks (ICML 2024 · similarity 0.88)
- Information-theoretic Limits of Online Classification with Noisy Labels (NeurIPS 2024 · 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.