Research map / Adversarial robustness and security / Certified and empirical robustness
Image Synthesis with a Single (Robust) Classifier
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 |
|---|---|---|---|
| generate by class-score maximization with a robust classifier vs BigGAN | image generation · ImageNet | Inception Score: 233.1 -> 259.0 | Helped |
| robust classifier generation vs BigGAN | image generation · ImageNet | FID: 7.4 -> 36.0 | Hurt |
| robust classifier generation vs BigGAN/WGAN-GP | image generation · CIFAR-10 | Inception Score: 9.22 -> 7.5 | Hurt |
| use adversarially robust instead of standard classifier for input-gradient synthesis | class-score maximization · ImageNet | perceptual quality | Helped |
Closest papers by meaning
- Synthesizing Robust Adversarial Examples (ICML 2018 · similarity 0.89)
- Benchmarking Neural Network Robustness to Common Corruptions and Perturbations (ICLR 2019 · similarity 0.88)
- Adversarially Robust Generalization Requires More Data (NeurIPS 2018 · similarity 0.88)
- Adversarial Robustness of Supervised Sparse Coding (NeurIPS 2020 · similarity 0.88)
- What It Thinks Is Important Is Important: Robustness Transfers Through Input Gradients (CVPR 2020 · similarity 0.88)
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 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.