Research map / Learning theory and algorithms / Combinatorial and search optimization
A Semidefinite Relaxation Based Branch-and-Bound Method for Tight Neural Network Verification
Jianglin Lan, Benedikt Brückner, Alessio Lomuscio
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 |
|---|---|---|---|
| Add eigenvector-based linear constraints and branch-and-bound to LayerSDP | LayerSDP · MNIST MLP-Adv | verified robustness: 91 -> 92 | Improved |
| Add eigenvector-based linear constraints and branch-and-bound to LayerSDP | LayerSDP · MNIST MLP-LP | verified robustness: 80 -> 80 | No clear effect |
| Add eigenvector-based linear constraints and branch-and-bound to LayerSDP | LayerSDP · MNIST MLP-SDP | verified robustness: 84 -> 84 | No clear effect |
| Add eigenvector-based linear constraints and branch-and-bound to LayerSDP | LayerSDP · MNIST MLP-6×100 | verified robustness: 75 -> 80 | Improved |
| Add eigenvector-based linear constraints and branch-and-bound to LayerSDP | LayerSDP · MNIST MLP-9×100 | verified robustness: 35 -> 47 | Improved |
| Use BaBSDP instead of β-CROWN | BaBSDP · MNIST MLP-9×100 | verified robustness: 69 -> 47 | Hurt |
| Add eigenvector-based linear constraints and branch-and-bound to LayerSDP | LayerSDP · MNIST MLP-6×200 | verified robustness: 92 -> 93 | Improved |
| Add eigenvector-based linear constraints and branch-and-bound to LayerSDP | LayerSDP · CIFAR10 CF-3×20 | verified robustness: 17 -> 18 | Improved |
Closest papers by meaning
- Iteratively Enhanced Semidefinite Relaxations for Efficient Neural Network Verification (AAAI 2023 · similarity 0.95)
- Tight Neural Network Verification via Semidefinite Relaxations and Linear Reformulations (AAAI 2022 · similarity 0.94)
- SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming (ICML 2025 · similarity 0.91)
- Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification (NeurIPS 2025 · similarity 0.86)
- Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes (NeurIPS 2024 · similarity 0.86)
- Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization (ICLR 2025 · similarity 0.85)
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.
