Incremental Verification of Neural Networks
Proceedings of the ACM on Programming Languages · 06.06.2023 · 7 (PLDI) · 1920-1945
DOI: 10.1145/3591299 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Programming Languages, online erschienen am 06.06.2023. Verfasst von Shubham Ugare und 3 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 73 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Ugare, S., Banerjee, D., Misailovic, S., & Singh, G. (2023). Incremental Verification of Neural Networks. Proceedings of the ACM on Programming Languages, 7(PLDI), 1920-1945. https://doi.org/10.1145/3591299
Vancouver
Ugare S, Banerjee D, Misailovic S, Singh G. Incremental Verification of Neural Networks. Proceedings of the ACM on Programming Languages. 2023;7(PLDI):1920-1945. doi:10.1145/3591299
BibTeX
@article{Ugare2023,
author = {Ugare, Shubham and Banerjee, Debangshu and Misailovic, Sasa and Singh, Gagandeep},
title = {Incremental Verification of Neural Networks},
journal = {Proceedings of the ACM on Programming Languages},
year = {2023},
volume = {7},
number = {PLDI},
pages = {1920--1945},
doi = {10.1145/3591299}
}
EUVIMED