Research map / Adversarial robustness and security / Certified and empirical robustness
Hierarchical Randomized Smoothing
Yan Scholten, Jan Schuchardt, Aleksandar Bojchevski, Stephan Günnemann
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 hierarchical smoothing instead of additive-noise or ablation certificates | GAT on Cora-ML · Cora-ML node classification | certified accuracy versus clean accuracy | Improved |
| Use hierarchical smoothing instead of Gaussian-noise or ablation certificates | ResNet50 on CIFAR10 · CIFAR10 image classification | certified accuracy versus clean accuracy | Improved |
| Increase the entity-selection probability (ablation) | Hierarchical smoothing · Cora-ML and CIFAR10 | robustness and clean accuracy | Mixed |
| Add skip-connections that forward target-node features unsmoothed (ablation) | Hierarchical and sparse smoothing for GNNs · Cora-ML node classification | certified accuracy versus clean accuracy | Improved |
| Append the selection-indicator column and use it at inference (ablation) | Hierarchical smoothing for GAT · Cora-ML node classification | certified accuracy versus clean accuracy | Improved |
Closest papers by meaning
- Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More (ICML 2020 · similarity 0.91)
- Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing (ICLR 2024 · similarity 0.89)
- Robust Representation Consistency Model via Contrastive Denoising (ICLR 2025 · similarity 0.88)
- Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness (NeurIPS 2024 · similarity 0.87)
- Clustered Randomized Smoothing for Stochastic Prediction Functions (NeurIPS 2026 · similarity 0.87)
- Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing (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.
