Reachability analysis of deep neural networks with provable guarantees

Ruan, Wenjie and Huang, Xiaowei and Kwiatkowska, Marta (2018) Reachability analysis of deep neural networks with provable guarantees. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. International Joint Conferences on Artificial Intelligence, SWE, pp. 2651-2659. ISBN 9780999241127

Full text not available from this repository.

Abstract

Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic reachability problem for feed-forward DNNs which, for a given set of inputs to the network and a Lipschitz-continuous function over its outputs, computes the lower and upper bound on the function values. Because the network and the function are Lipschitz continuous, all values in the interval between the lower and upper bound are reachable. We show how to obtain the safety verification problem, the output range analysis problem and a robustness measure by instantiating the reachability problem. We present a novel algorithm based on adaptive nested optimisation to solve the reachability problem. The technique has been implemented and evaluated on a range of DNNs, demonstrating its efficiency, scalability and ability to handle a broader class of networks than state-of-the-art verification approaches.

Item Type:
Contribution in Book/Report/Proceedings
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1700/1702
Subjects:
ID Code:
133220
Deposited By:
Deposited On:
26 Apr 2019 12:25
Refereed?:
Yes
Published?:
Published
Last Modified:
01 Jul 2020 08:12