A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability
University of Liverpool · University of Oxford · +3 more institutions
Indexed incrossref
Abstract
No abstract available for this paper.
Citation impact
496
total citations
- FWCI
- 37.95
- Percentile
- 100%
- References
- 330
Citations per year
Authors
8Topics & keywords
Topics
Keywords
- Interpretability
- Trustworthiness
- Adversarial system
- Computer science
- Software deployment
- Deep neural networks
- Computer security
- Artificial intelligence
No related works found for this paper.