Towards Global Neural Network Abstractions with Locally-Exact Reconstruction

Research output: Contribution to journalArticlepeer-review

Abstract

Neural networks are a powerful class of non-linear functions. However, their
black-box nature makes it difficult to explain their behaviour and certify
their safety. Abstraction techniques address this challenge by transforming
the neural network into a simpler, over-approximated function. Unfortunately,
existing abstraction techniques are slack, which limits their applicability
to small local regions of the input domain. In this paper, we propose
Global Interval Neural Network Abstractions with Center-Exact Reconstruction
(GINNACER). Our novel abstraction technique produces sound overapproximation
bounds over the whole input domain while guaranteeing exact
reconstructions for any given local input. Our experiments show that GINNACER
is several orders of magnitude tighter than state-of-the-art global
abstraction techniques, while being competitive with local ones.
Original languageEnglish
JournalNeural Networks
Publication statusPublished - 2023

Fingerprint

Dive into the research topics of 'Towards Global Neural Network Abstractions with Locally-Exact Reconstruction'. Together they form a unique fingerprint.

Cite this