A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees
- Submitting institution
-
The University of Liverpool
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 12128
- Type
- D - Journal article
- DOI
-
10.1016/j.tcs.2019.05.046
- Title of journal
- Theoretical Computer Science
- Article number
- -
- First page
- 298
- Volume
- 807
- Issue
- -
- ISSN
- 0304-3975
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 7
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- A preliminary version of this paper with the title "Feature-guided black-box safety testing of deep neural networks" appeared in TACAS'18. This paper is part of a research programme by Huang and co-authors into the verification of deep neural networks. This approach has been further developed by Huang et al in "Reachability Analysis of Deep Neural Networks with Provable Guarantees" (IJCAI'18) and "Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the Hamming Distance" (IJCAI'19), both not REF returned.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -