Research map / Adversarial robustness and security / Certified and empirical robustness
Fast and Effective Robustness Certification
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 area-minimizing pointwise Zonotope ReLU transformer instead of linear-bound backprop (Fast-Lin) | robustness verifier · MNIST FFNNSmall ReLU | runtime: up to 2.5x faster | Helped |
| use specialized ReLU transformer instead of generic join-based AI2 transformer | Zonotope verifier · MNIST FFNNSmall ReLU | verified robustness | Helped |
| defend network with DiffAI/PGD training | CIFAR10 FFNNBig ReLU · CIFAR10 | verified robustness | No clear effect |
| defend network with DiffAI/PGD training | CIFAR10 ConvSmall ReLU · CIFAR10 | verified robustness | Helped |
Closest papers by meaning
- Certified but Private: Scalable Zero-Knowledge Proofs for the Formal Verification of Neural Networks (NeurIPS 2026 · similarity 0.88)
- Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone (CVPR 2025 · similarity 0.88)
- VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees (ICML 2024 · similarity 0.88)
- Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation (CVPR 2024 · similarity 0.87)
- A Recipe for Improved Certifiable Robustness (ICLR 2024 · similarity 0.87)
- Interpreting Robustness Proofs of Deep Neural Networks (ICLR 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.