Research map / Adversarial robustness and security / Certified and empirical robustness
MultiRobustBench: Benchmarking Robustness Against Multiple 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 |
|---|---|---|---|
| Evaluate defenses across multiple attack types and strengths using CR_ind-avg | 16 existing defenses · CIFAR-10 | CR_ind-avg: 67.76 | Mixed |
| Evaluate defenses against the worst-case attack using CR_ind-worst | 16 existing defenses · CIFAR-10 | CR_ind-worst: 3.30 | Hurt |
| Train with additional synthetic data (ablation) | PAT-trained models · CIFAR-10 | CR_ind-avg: 69.14 | Helped |
| Train with additional synthetic data (ablation) | PAT-trained models · CIFAR-10 | CR_ind-worst | No clear effect |
| Use smaller architectures (ResNet-18 or ResNet-34) instead of larger architectures (ablation) | Adversarially trained models · CIFAR-10 | CR | Helped |
| Use smaller architectures (ResNet-18 or ResNet-34) instead of larger architectures (ablation) | Adversarially trained models · CIFAR-10 | stability constant | Helped |
| Train for more epochs (ablation) | Adversarially trained models · CIFAR-10 | CR_ind-avg | Helped |
| Train for more epochs (ablation) | Adversarially trained models · CIFAR-10 | CR_ind-worst | Hurt |
| Train for more epochs (ablation) | Adversarially trained models · CIFAR-10 | stability constant | Hurt |
| Add training data (ablation) | PAT-trained models · CIFAR-10 | stability constant | No clear effect |
Closest papers by meaning
- AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples (AAAI 2025 · similarity 0.87)
- Rethinking the Adversarial Robustness of Multi-Exit Neural Networks in an Attack-Defense Game (CVPR 2025 · similarity 0.87)
- On the Robustness of Distributed Machine Learning Against Transfer Attacks (AAAI 2025 · similarity 0.86)
- Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks (CVPR 2025 · similarity 0.86)
- OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift (ICML 2024 · similarity 0.86)
- Efficient Robustness Evaluation via Constraint Relaxation (AAAI 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.