{"type":"ScholarlyArticle","title":"DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis","authors":[{"name":"Patrick Henriksen","slug":"patrick-henriksen","given":"Patrick","family":"Henriksen","affiliation":""},{"name":"Alessio Lomuscio","slug":"alessio-lomuscio","given":"Alessio","family":"Lomuscio","affiliation":""}],"abstract":"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 1–2 orders of magnitude and 21-34% fewer timeouts when compared to the current SoA toolkits.","doi":"10.24963/ijcai.2021/351","url":"https://ijcai.org/proceedings/2021/351","pdf":"https://ijcai.org/proceedings/2021/0351.pdf","markdown":"https://ijcai.org/proceedings/2021/351.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/351","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Machine Learning","track":"Main Track","number":351,"pages":{"first":2549,"last":2555},"keywords":["Machine Learning: Deep Learning","Multidisciplinary Topics and Applications: Validation and Verification"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}