Research map / Adversarial robustness and security / Certified and empirical robustness
Lower bounds on the robustness to adversarial perturbations
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 |
|---|---|---|---|
| Layer-wise theoretical lower bound on adversarial perturbation norm (vs. empirical FGS norms) | LeNet · MNIST and CIFAR-10 test sets | violations of bound | No clear effect |
| Bounds computed as lower bounds on perturbation norm, compared to FGS empirical norms | LeNet · MNIST and CIFAR-10 test sets | gap between bound and empirical perturbation norm | Mixed |
| Model-level LeNet accuracy comparison: MNIST vs CIFAR-10 perturbation magnitude | LeNet · MNIST vs CIFAR-10 | normalized adversarial perturbation norm | Mixed |
Closest papers by meaning
- Adversarial vulnerability for any classifier (NeurIPS 2018 · similarity 0.92)
- Learning perturbation sets for robust machine learning (ICLR 2021 · similarity 0.90)
- Wide Two-Layer Networks can Learn from Adversarial Perturbations (NeurIPS 2024 · similarity 0.90)
- Contrasting Adversarial Perturbations: The Space of Harmless Perturbations (AAAI 2025 · similarity 0.90)
- Theoretical Understanding of Learning from Adversarial Perturbations (ICLR 2024 · similarity 0.90)
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (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.