IEEE 3129-2023
$33.58
IEEE Standard for Robustness Testing and Evaluation of Artificial Intelligence (AI)-based Image Recognition Service (Published)
Published By | Publication Date | Number of Pages |
IEEE | 2023 | 34 |
New IEEE Standard – Active. Test specifications with a set of indicators for common corruption and adversarial attacks, which can be used to evaluate the robustness of artificial intelligence-based image recognition services are provided in this standard. Robustness attack threats and establishes an assessment framework to evaluate the robustness of artificial intelligence-based image recognition service under various settings are also specified in this standard.
PDF Catalog
PDF Pages | PDF Title |
---|---|
1 | IEEE Std 3129™-2023 Front cover |
2 | Title page |
4 | Important Notices and Disclaimers Concerning IEEE Standards Documents |
8 | Participants |
10 | Introduction |
11 | Contents |
12 | 1. Overview 1.1 Scope 1.2 Purpose 1.3 Word usage |
13 | 2. Normative references 3. Definitions, acronyms, and abbreviations 3.1 Definitions 3.2 Acronyms and abbreviations 4. Robustness evaluation framework for AI-based image recognition services 4.1 Background |
14 | 4.2 Image corruptions |
15 | 4.3 Adversarial attacks |
16 | 4.4 Evaluation practice 4.5 Roles |
17 | 4.6 Evaluation process |
18 | 4.7 Evaluation metrics |
24 | 5. Test cases 5.1 Test case for Accuracy test 5.2 Test case for common corruptions 5.3 Test case for style transfer |
25 | 5.4 Test case for adversarial perturbations |
26 | Annex A (informative) Example common corruptions and adversarial attacks A.1 Examples of common corruptions |
27 | A.2 Example adversarial attacks |
30 | Annex B (informative) Example evaluation |
31 | Annex C (informative) Bibliography |
34 | Back cover |