Research map / Adversarial robustness and security / Certified and empirical robustness
Are adversarial examples inevitable?
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 |
|---|---|---|---|
| Increase image resolution by duplicating each MNIST pixel into a larger block | Naturally trained MNIST classifiers · MNIST and big MNIST | adversarial susceptibility | Hurt |
| Increase image resolution while adversarially training | Adversarially trained MNIST classifiers · MNIST and big MNIST | perturbation size at susceptibility transition | No clear effect |
| Use CIFAR-10 instead of big MNIST at similar dimensionality | Image classifiers · CIFAR-10 and big MNIST | adversarial susceptibility | Hurt |
| Apply adversarial training | MNIST and CIFAR-10 classifiers · MNIST and CIFAR-10 | adversarial susceptibility | Mixed |
Closest papers by meaning
- Adversarial Examples Are Not Bugs, They Are Features (NeurIPS 2019 · similarity 0.93)
- Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-uniform Attacks (AAAI 2021 · similarity 0.93)
- Adversarial Risk and the Dangers of Evaluating Against Weak Attacks (ICML 2018 · similarity 0.91)
- One Man's Trash Is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examples (CVPR 2020 · similarity 0.90)
- On Adversarial Training without Perturbing all Examples (ICLR 2024 · similarity 0.90)
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 2025 · similarity 0.89)
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.