Verification of Neural Networks’ Global Robustness
Proceedings of the ACM on Programming Languages · 29.04.2024 · 8 (OOPSLA1) · 1010-1039
DOI: 10.1145/3649847 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Programming Languages, online erschienen am 29.04.2024. Verfasst von Anan Kabaha und 1 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Israel Science Foundation.
Abstract (Originalsprache)
Neural networks are successful in various applications but are also susceptible to adversarial attacks. To show the safety of network classifiers, many verifiers have been introduced to reason about the local robustness of a given input to a given perturbation. While successful, local robustness cannot generalize to unseen inputs. Several works analyze global robustness properties, however, neither can provide a precise guarantee about the cases where a network classifier does not change its classification. In this work, we propose a new global robustness property for classifiers aiming at finding the minimal globally robust bound, which naturally extends the popular local robustness property for classifiers. We introduce VHAGaR, an anytime verifier for computing this bound. VHAGaR relies on three main ideas: encoding the problem as a mixed-integer programming and pruning the search space by identifying dependencies stemming from the perturbation or the network's computation and generalizing adversarial attacks to unknown inputs. We evaluate VHAGaR on several datasets and classifiers and show that, given a three hour timeout, the average gap between the lower and upper bound on the minimal globally robust bound computed by VHAGaR is 1.9, while the gap of an existing global robustness verifier is 154.7. Moreover, VHAGaR is 130.6x faster than this verifier. Our results further indicate that leveraging dependencies and adversarial attacks makes VHAGaR 78.6x faster.
Förderung
- Israel Science Foundation
Zitieren
APA
Kabaha, A., & Cohen, D. D. (2024). Verification of Neural Networks’ Global Robustness. Proceedings of the ACM on Programming Languages, 8(OOPSLA1), 1010-1039. https://doi.org/10.1145/3649847
Vancouver
Kabaha A, Cohen DD. Verification of Neural Networks’ Global Robustness. Proceedings of the ACM on Programming Languages. 2024;8(OOPSLA1):1010-1039. doi:10.1145/3649847
BibTeX
@article{Kabaha2024,
author = {Kabaha, Anan and Cohen, Dana Drachsler},
title = {Verification of Neural Networks’ Global Robustness},
journal = {Proceedings of the ACM on Programming Languages},
year = {2024},
volume = {8},
number = {OOPSLA1},
pages = {1010--1039},
doi = {10.1145/3649847}
}
EUVIMED