Research map / Adversarial robustness and security / Certified and empirical robustness
Are Generative Classifiers More Robust to Adversarial Attacks?
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 black-box SPSA instead of white-box PGD | GFZ, GBZ, GBY, and GFY · MNIST and CIFAR-binary | victim accuracy: MNIST: GFZ 4.0% -> 68.2%; GBZ 29.7% -> 79.0%; GBY 7.4% -> 71.0%; GFY 2.3% -> 55.9%. CIFAR-binary: GFZ 67.7% -> 96.4%; GB | Helped |
| Use the bottleneck structure (GBZ) rather than fully connected structure (GFZ) (ablation) | Deep Bayes classifier · CIFAR-binary, white-box PGD, ε=0.05 | victim accuracy: 67.7% -> 83.9% | Helped |
| Use the bottleneck structure (GBY) rather than fully connected structure (GFY) (ablation) | Deep Bayes classifier · MNIST, white-box PGD, ε=0.3 | victim accuracy: 2.3% -> 7.4% | Helped |
Closest papers by meaning
- On the Existence of The Adversarial Bayes Classifier (NeurIPS 2021 · similarity 0.89)
- Adversarial vulnerability for any classifier (NeurIPS 2018 · similarity 0.88)
- Understanding the Limitations of Conditional Generative Models (ICLR 2020 · similarity 0.88)
- Analyzing the Robustness of Nearest Neighbors to Adversarial Examples (ICML 2018 · similarity 0.88)
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 2025 · similarity 0.85)
- Robust Classification via a Single Diffusion Model (ICML 2024 · similarity 0.85)
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.