Robustness of Deep ReLU Networks to Misclassification of High-Dimensional Data

Věra Kůrková
2/21/2026
cs.LGcs.NE

No confident code implementation found for this paper.

Abstract

We present a theoretical study of the robustness of parameterized networks to random input perturbations. Specifically, we analyze local robustness at a given network input by quantifying the probability that a small additive random perturbation of the input leads to misclassification. For deep networks with rectified linear units, we derive lower bounds on local robustness in terms of the input dimensionality and the total number of network units.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets

83% match2025

On the Local Complexity of Linear Regions in Deep ReLU Networks

81% match2024

Robustness of neural networks to random noise perturbations of their inputs

81% match1 repo2026

Make Interval Bound Propagation great again

80% match1 repo32024

Scaling provable adversarial defenses

80% match1 repo3922018

Natural Geometry of Robust Data Attribution: From Convex Models to Deep Networks

80% match2025

Cite this paper

@article{krkov2026robustness,
  title  = {Robustness of Deep ReLU Networks to Misclassification of High-Dimensional Data},
  author = {Věra Kůrková},
  year   = {2026},
  eprint = {2602.18674},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2602.18674v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2602.18674.svg)](https://codeofpaper.com/paper/2602.18674)

Discussion