BS ISO/IEC 24029-2:2023 2024
$142.49
Artificial intelligence (AI). Assessment of the robustness of neural networks – Methodology for the use of formal methods
Published By | Publication Date | Number of Pages |
BSI | 2024 | 32 |
PDF Catalog
PDF Pages | PDF Title |
---|---|
2 | undefined |
6 | Foreword |
7 | Introduction |
9 | 1 Scope 2 Normative references 3 Terms and definitions |
12 | 4 Abbreviated terms 5 Robustness assessment 5.1 General |
13 | 5.2 Notion of domain |
14 | 5.3 Stability 5.3.1 Stability property 5.3.2 Stability criterion 5.4 Sensitivity 5.4.1 Sensitivity property |
15 | 5.4.2 Sensitivity criterion 5.5 Relevance 5.5.1 Relevance property 5.5.2 Relevance criterion |
16 | 5.6 Reachability 5.6.1 Reachability property 5.6.2 Reachability criterion |
17 | 6 Applicability of formal methods on neural networks 6.1 Types of neural network concerned 6.1.1 Architectures of neural networks |
18 | 6.1.2 Neural networks input data type |
20 | 6.2 Types of formal methods applicable 6.2.1 General |
21 | 6.2.2 Solver 6.2.3 Abstract interpretation 6.2.4 Reachability analysis in deterministic environments |
22 | 6.2.5 Reachability analysis in non-deterministic environments 6.2.6 Model checking 6.3 Summary |
23 | 7 Robustness during the life cycle 7.1 General 7.2 During design and development 7.2.1 General 7.2.2 Identifying the recognized features |
24 | 7.2.3 Checking separability 7.3 During verification and validation 7.3.1 General |
25 | 7.3.2 Covering parts of the input domain 7.3.3 Measuring perturbation impact |
26 | 7.4 During deployment |
27 | 7.5 During operation and monitoring 7.5.1 General 7.5.2 Robustness on a domain of operation |
28 | 7.5.3 Changes in robustness |
29 | Bibliography |