Incremental Verification of Neural Networks

Shubham Ugare, Debangshu Banerjee, Sasa Misailovic, Gagandeep Singh

Research output: Contribution to journalArticlepeer-review

Abstract

Complete verification of deep neural networks (DNNs) can exactly determine whether the DNN satisfies a desired trustworthy property (e.g., robustness, fairness) on an infinite set of inputs or not. Despite the tremendous progress to improve the scalability of complete verifiers over the years on individual DNNs, they are inherently inefficient when a deployed DNN is updated to improve its inference speed or accuracy. The inefficiency is because the expensive verifier needs to be run from scratch on the updated DNN. To improve efficiency, we propose a new, general framework for incremental and complete DNN verification based on the design of novel theory, data structure, and algorithms. Our contributions implemented in a tool named IVAN yield an overall geometric mean speedup of 2.4x for verifying challenging MNIST and CIFAR10 classifiers and a geometric mean speedup of 3.8x for the ACAS-XU classifiers over the state-of-the-art baselines.

Original languageEnglish (US)
Pages (from-to)1920-1945
Number of pages26
JournalProceedings of the ACM on Programming Languages
Volume7
DOIs
StatePublished - Jun 6 2023

Keywords

  • Deep Neural Networks
  • Robustness
  • Verification

ASJC Scopus subject areas

  • Software
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Incremental Verification of Neural Networks'. Together they form a unique fingerprint.

Cite this