Research map / Adversarial robustness and security / Certified and empirical robustness
Towards Optimal Branching of Linear and Semidefinite Relaxations for Neural Network Robustness Certification
Brendon G. Anderson, Ziye Ma, Jingqi Li, Somayeh Sojoudi
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 |
|---|---|---|---|
| Replace filtered smart branching with the proposed worst-case-optimal LP branching scheme | Branch-and-bound LP certification · MNIST, CIFAR-10, Wisconsin breast cancer classifiers | percentage of test samples certified | Improved |
| Use the SDP relaxation with the proposed branching instead of branched LP | Branch-and-bound certification · MNIST, CIFAR-10, Wisconsin breast cancer classifiers | percentage of test samples certified | Improved |
| Extend the single-hidden-layer branching scheme to a multi-layer heuristic | LP branching · Large-scale deep network certification | certification performance | No clear effect |
Closest papers by meaning
- A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks (NeurIPS 2019 · similarity 0.91)
- Semidefinite relaxations for certifying robustness to adversarial examples (NeurIPS 2018 · similarity 0.90)
- Expressivity of ReLU-Networks under Convex Relaxations (ICLR 2024 · similarity 0.90)
- Convex Formulations for Training Two-Layer ReLU Neural Networks (ICLR 2025 · similarity 0.89)
- Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone (CVPR 2025 · similarity 0.88)
- Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation (CVPR 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.
