Research map / Adversarial robustness and security / Certified and empirical robustness
Adversarial Robustness through Disentangled Representations
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 DRRDN instead of TRADES | MNIST classifier · MNIST PGD40 | accuracy: 96.95 -> 97.55 | Helped |
| use DRRDN instead of TRADES | CIFAR10 classifier · CIFAR10 PGD40 | accuracy: 50.91 -> 52.32 | Helped |
| add mutual-information minimization (ablation) | DRRDN · MNIST PGD40 | accuracy: 96.88% -> 97.55% | Helped |
| add mutual-information minimization (ablation) | DRRDN · MNIST PGD100 | accuracy: 96.25% -> 96.78% | Helped |
| add reconstruction loss (ablation) | DRRDN · MNIST PGD40 | accuracy: 97.32% -> 97.55% | Helped |
| add reconstruction loss (ablation) | DRRDN · MNIST PGD100 | accuracy: 96.43% -> 96.78% | Helped |
Closest papers by meaning
- Understanding Robust Learning through the Lens of Representation Similarities (NeurIPS 2022 · similarity 0.89)
- Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement (AAAI 2025 · similarity 0.88)
- Learning Better Certified Models from Empirically-Robust Teachers (NeurIPS 2026 · similarity 0.87)
- ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck (ICML 2025 · similarity 0.86)
- Robustness Reprogramming for Representation Learning (ICLR 2025 · similarity 0.86)
- 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.