Skip to main navigation Skip to search Skip to main content

Symbolic Gaussian Smoothing

  • Stony Brook University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This work introduces a deterministic variant of randomized smoothing for certifying neural network robustness. Instead of relying on multiple stochastic forward passes with Gaussian noise, the proposed method employs symbolic moment propagation to analytically compute the exact mean and covariance of the output distribution in a single pass. Evaluations on MNIST and Fashion MNIST show that the method yields comparable classification accuracy while achieving, on average, 10% larger certified robustness radii. This deterministic framework offers exact, non-probabilistic guarantees that are particularly attractive for safety-critical applications.

Original languageEnglish
Title of host publicationProceedings of the ACM/IEEE 16th International Conference on Cyber-Physical Systems, ICCPS 2025, held as part of the CPS-IoT Week 2025
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9798400714986
DOIs
StatePublished - May 7 2025
Event16th Annual ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2025, held as part of the CPS-IoT Week 2025 - Irvine, United States
Duration: May 6 2025May 9 2025

Publication series

NameProceedings of the ACM/IEEE 16th International Conference on Cyber-Physical Systems, ICCPS 2025, held as part of the CPS-IoT Week 2025

Conference

Conference16th Annual ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2025, held as part of the CPS-IoT Week 2025
Country/TerritoryUnited States
CityIrvine
Period05/6/2505/9/25

Keywords

  • Certified Defense
  • Neural Network Robustness

Fingerprint

Dive into the research topics of 'Symbolic Gaussian Smoothing'. Together they form a unique fingerprint.

Cite this