Research map / Adversarial robustness and security / Certified and empirical robustness
Most ReLU Networks Suffer from $\ell^2$ 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 |
|---|---|---|---|
| Use gradient flow to search for a sign-flipping perturbation | Random ReLU networks whose layers decrease in dimension · Fixed nonzero input | Euclidean perturbation distance: \tilde O\left(\frac{\|x_0\|}{\sqrt{d}}\right) | Helped |
| Use gradient flow to search for a sign-flipping perturbation | Random ReLU networks whose layers decrease in dimension · Any input distribution | Euclidean perturbation distance: \tilde O\left(\frac{\|x_0\|}{\sqrt{d}}\right) | Helped |
Closest papers by meaning
- Adversarial Examples in Multi-Layer Random ReLU Networks (NeurIPS 2021 · similarity 0.92)
- Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces (NeurIPS 2023 · similarity 0.90)
- Activation-Descent Regularization for Input Optimization of ReLU Networks (ICML 2024 · similarity 0.89)
- Wide Two-Layer Networks can Learn from Adversarial Perturbations (NeurIPS 2024 · similarity 0.87)
- Contrasting Adversarial Perturbations: The Space of Harmless Perturbations (AAAI 2025 · similarity 0.86)
- On the Local Complexity of Linear Regions in Deep ReLU Networks (ICML 2025 · similarity 0.86)
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.