BibTex format
@inproceedings{Henriksen:2021,
author = {Henriksen, P and Lomuscio, A},
pages = {2549--2555},
title = {DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis},
year = {2021}
}
Publications
Citation
RIS format (EndNote, RefMan)
TY - CPAPER
AB - We propose a novel, complete algorithm for the verification and analysis of feed-forward, ReLU-based neural networks. The algorithm, based on symbolic interval propagation, introduces a new method for determining split-nodes which evaluates the indirect effect that splitting has on the relaxations of successor nodes. We combine this with a new efficient linear-programming encoding of the splitting constraints to further improve the algorithm's performance. The resulting implementation, DEEPSPLIT, achieved speedups of around 1-2 orders of magnitude and 21-34% fewer timeouts when compared to the current SoA toolkits.
AU - Henriksen,P
AU - Lomuscio,A
EP - 2555
PY - 2021///
SN - 1045-0823
SP - 2549
TI - DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis
ER -