Research map / Adversarial robustness and security / Certified and empirical robustness
Adversarial vulnerability for any classifier
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 |
|---|---|---|---|
| Add PGD adversarial training to Wide ResNet | Wide ResNet · CIFAR-10 | In-distribution robustness: 5.9 × 10^{-3} -> 8.3 × 10^{-3} | Helped |
| Add PGD adversarial training to Wide ResNet | Wide ResNet · CIFAR-10 | Unconstrained robustness: 0.20 × 10^{-3} -> 2.0 × 10^{-3} | Helped |
| Add PGD adversarial training to Wide ResNet | Wide ResNet · CIFAR-10 | Error rate: 3.9 % -> 16.0 % | Hurt |
Closest papers by meaning
- Lower bounds on the robustness to adversarial perturbations (NeurIPS 2017 · similarity 0.92)
- Why adversarial training can hurt robust accuracy (ICLR 2023 · similarity 0.91)
- On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification (ICML 2026 · similarity 0.91)
- NAG: Network for Adversary Generation (CVPR 2018 · similarity 0.91)
- Adversarial Robustness of Supervised Sparse Coding (NeurIPS 2020 · similarity 0.91)
- Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution (NeurIPS 2018 · similarity 0.91)
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.