Research map / Learning theory and algorithms / Combinatorial and search optimization
Iteratively Enhanced Semidefinite Relaxations for Efficient Neural Network Verification
Jianglin Lan, Yang Zheng, 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 the proposed nonlinear constraints and iterative auxiliary SDP solving to LayerSDP | LayerSDP · MLP-Adv | verified robustness (%): 91 -> 92 | Improved |
| Add the proposed nonlinear constraints and iterative auxiliary SDP solving to LayerSDP | LayerSDP · MLP-LP | verified robustness (%): 80 -> 80 | No clear effect |
| Add the proposed nonlinear constraints and iterative auxiliary SDP solving to LayerSDP | LayerSDP · MLP-SDP | verified robustness (%): 84 -> 84 | No clear effect |
| Add the proposed nonlinear constraints and iterative auxiliary SDP solving to LayerSDP | LayerSDP · MLP-6×100 | verified robustness (%): 75 -> 83 | Improved |
| Add the proposed nonlinear constraints and iterative auxiliary SDP solving to LayerSDP | LayerSDP · MLP-9×100 | verified robustness (%): 35 -> 47 | Improved |
| Add the proposed nonlinear constraints and iterative auxiliary SDP solving to LayerSDP | LayerSDP · MLP-6×200 | verified robustness (%): 92 -> 94 | Improved |
| Add the proposed nonlinear constraints and iterative auxiliary SDP solving to LayerSDP | LayerSDP · MLP-8×1024-0.1 | verified robustness (%): 83 -> 86 | Improved |
| Add the proposed nonlinear constraints and iterative auxiliary SDP solving to LayerSDP | LayerSDP · MLP-8×1024-0.3 | verified robustness (%): 28 -> 33 | Improved |
| Add the proposed nonlinear constraints and iterative auxiliary SDP solving to LayerSDP | LayerSDP · CF-3×20 | verified robustness (%): 17 -> 18 | Improved |
Closest papers by meaning
- A Semidefinite Relaxation Based Branch-and-Bound Method for Tight Neural Network Verification (AAAI 2023 · similarity 0.95)
- SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming (ICML 2025 · similarity 0.90)
- Convex Formulations for Training Two-Layer ReLU Neural Networks (ICLR 2025 · similarity 0.87)
- Expressivity of ReLU-Networks under Convex Relaxations (ICLR 2024 · similarity 0.87)
- Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time (ICML 2024 · similarity 0.87)
- Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization (ICLR 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.
