Research map / Learning theory and algorithms / Combinatorial and search optimization
Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification
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 |
|---|---|---|---|
| add per-neuron split constraints (beta) to CROWN bound propagation in BaB | CROWN-based BaB (Fast-and-Complete) · CIFAR-10 Base | avg verification time (s): 695.01 -> 226.06 | Helped |
| use FSB branching instead of BaBSR (ablation) | β-CROWN · CIFAR-10 Base | avg verification time (s): 226.06 -> 118.23 | Helped |
| β-CROWN FSB vs PRIMA multi-neuron relaxation | incomplete verification · MNIST MLP 8x100 | verified accuracy (%): 42.8 -> 62.0 | Helped |
| β-CROWN FSB vs PRIMA | incomplete verification · CIFAR ResNet | verified accuracy (%) | No clear effect |
| β-CROWN FSB vs SDP-FO | adversarially trained CNNs · MNIST CNN-A-Adv | verified accuracy (%): 43.4 -> 70.5 | Helped |
| compute intermediate bounds with MIP before BaB | β-CROWN FSB on small MLPs · MNIST MLPs | verified accuracy | Helped |
Closest papers by meaning
- SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming (ICML 2025 · similarity 0.94)
- Towards Evaluating and Training Verifiably Robust Neural Networks (CVPR 2021 · similarity 0.92)
- Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification (NeurIPS 2025 · similarity 0.90)
- Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes (NeurIPS 2024 · similarity 0.88)
- DeepBern-Nets: Taming the Complexity of Certifying Neural Networks Using Bernstein Polynomial Activations and Precise Bound Propagation (AAAI 2024 · similarity 0.87)
- Dynamic Back-Substitution in Bound-Propagation-Based Neural Network Verification (AAAI 2025 · 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.