AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

FocusBranch: Combinatorial Branch-and-Bound for $\ell_0$ Neural Network Robustness Verification

Renwei Deng, Yang He, Linyi Li, Yuepeng Wang

NeurIPS 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Neural network robustness verification · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes FocusBranch, a combinatorial branch-and-bound verifier for l0 local robustness of neural networks that decomposes the l0-ball into focus-pixel-set nodes.

Problem

Verifying local robustness of neural networks under l0 perturbations is combinatorial because a verifier must reason over all sparse subsets of perturbed pixels.

Approach

Decomposes the l0-ball into branch-and-bound nodes, each consisting of a focus pixel set S and a complementary component, so verification proceeds by combinatorially branching over pixel subsets rather than treating the whole l0-ball at once.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add concrete-node branching (adaptive starting level below eps) on top of super-node branching (ablation)FocusBranch · MNIST afc5, eps=5verified instances (of 70): 56 -> 61Improved
add super-node (covering design) branching on top of concrete-node branching (ablation)FocusBranch · MNIST afc5, eps=5verified instances (of 70): 49 -> 61Improved
use node abstraction with sampled starting level instead of always starting at level eps (CVD-TT)FocusBranch vs CVD-TT · l0 verification, eps=5verified instances (of 740): 375 -> 641Improved
increase perturbation budget eps from 3 to 6FocusBranch · l0 verification, all networksverified rate: 99.8% -> 98.8% -> 86.6% (eps 3,4,5)Hurt
batch node bounding in FocusBranch (batching enabled)FocusBranch on CNNs · l0 verification, eps=5, CNNsverified instancesImproved

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