Research map / Adversarial robustness and security / Certified and empirical robustness
Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them
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 |
|---|---|---|---|
| Reduction: convert detector claims (robust detection at eps) into implied inefficient classifier robustness at eps/2 | 14 published detector defenses · MNIST, CIFAR-10, ImageNet | implied robust accuracy vs. state-of-the-art classifier at eps/2 | Hurt |
| Certified detector vs. certified classifier comparison | CIFAR-10 l_inf certified defenses · CIFAR-10 certified | robust accuracy with detection vs. classification: within ±2% | No clear effect |
Closest papers by meaning
- Adversarial Examples Are Not Bugs, They Are Features (NeurIPS 2019 · similarity 0.91)
- GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification (ICLR 2020 · similarity 0.91)
- Are adversarial examples inevitable? (ICLR 2019 · similarity 0.90)
- Adversarial Risk and the Dangers of Evaluating Against Weak Attacks (ICML 2018 · similarity 0.89)
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 2025 · similarity 0.87)
- Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective (NeurIPS 2024 · similarity 0.87)
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.