LIPIcs.CONCUR.2019.1.pdf
- Filesize: 1.36 MB
- 5 pages
Document
Safety Verification for Deep Neural Networks with Provable Guarantees (Invited Paper)
Author
Marta Z. Kwiatkowska 
- Publication date: 2019-08-20
- License:
Creative Commons Attribution 3.0 Unported license
-
Part of:
Volume:
30th International Conference on Concurrency Theory (CONCUR 2019)
Series: Leibniz International Proceedings in Informatics (LIPIcs)
Conference: International Conference on Concurrency Theory (CONCUR)
File
Document Identifiers
Author Details
Cite AsGet BibTex
Marta Z. Kwiatkowska. Safety Verification for Deep Neural Networks with Provable Guarantees (Invited Paper). In 30th International Conference on Concurrency Theory (CONCUR 2019). Leibniz International Proceedings in Informatics (LIPIcs), Volume 140, pp. 1:1-1:5, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2019)
https://doi.org/10.4230/LIPIcs.CONCUR.2019.1
https://doi.org/10.4230/LIPIcs.CONCUR.2019.1
Abstract
Computing systems are becoming ever more complex, increasingly often incorporating deep learning components. Since deep learning is unstable with respect to adversarial perturbations, there is a need for rigorous software development methodologies that encompass machine learning. This paper describes progress with developing automated verification techniques for deep neural networks to ensure safety and robustness of their decisions with respect to input perturbations. This includes novel algorithms based on feature-guided search, games, global optimisation and Bayesian methods.
Subject Classification
ACM Subject Classification
- Theory of computation → Logic and verification
- Computing methodologies → Neural networks
Keywords
- Neural networks
- robustness
- formal verification
- Bayesian neural networks
Metrics
- Access Statistics
-
Total Accesses (updated on a weekly basis)
0PDF Downloads