AI Paper Atlas

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

JMLR 2025 · Adversarial robustness and security › Certified and empirical robustness · approach: Neural network robustness verification

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 changedWhereMeasuredEffect
Replace filtered smart branching with the proposed worst-case-optimal LP branching schemeBranch-and-bound LP certification · MNIST, CIFAR-10, Wisconsin breast cancer classifierspercentage of test samples certifiedImproved
Use the SDP relaxation with the proposed branching instead of branched LPBranch-and-bound certification · MNIST, CIFAR-10, Wisconsin breast cancer classifierspercentage of test samples certifiedImproved
Extend the single-hidden-layer branching scheme to a multi-layer heuristicLP branching · Large-scale deep network certificationcertification performanceNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy