Towards Scalable Complete Verification of Relu Neural Networks via Dependency-based Branching

Panagiotis Kouvaros; Alessio Lomuscio

IJCAI 2021poster50 citations

Towards Scalable Complete Verification of Relu Neural Networks via Dependency-based Branching

Abstract

We introduce an efficient method for the complete verification of ReLU-based feed-forward neural networks. The method implements branching on the ReLU states on the basis of a notion of dependency between the nodes. This results in dividing the original verification problem into a set of sub-problems whose MILP formulations require fewer integrality constraints. We evaluate the method on all of the ReLU-based fully connected networks from the first competition for neural network verification. The experimental results obtained show 145% performance gains over the present state-of-the-art in complete verification.

Machine Learning: Deep LearningMultidisciplinary Topics and Applications: Validation and Verification

BibTeX

@inproceedings{ijcai2021p364,
  title     = {Towards Scalable Complete Verification of Relu Neural Networks via Dependency-based Branching},
  author    = {Kouvaros, Panagiotis and Lomuscio, Alessio},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Zhi-Hua Zhou},
  pages     = {2643--2650},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/364},
  url       = {https://doi.org/10.24963/ijcai.2021/364},
}