Shopping Cart

No products in the cart.

IEEE 3168-2024

$23.33

IEEE Standard for Robustness Evaluation Test Methods for a Natural Language Processing Service That Uses Machine Learning (Approved Draft)

Published By Publication Date Number of Pages
IEEE 2024 29
Guaranteed Safe Checkout
Category:

If you have any questions, feel free to reach out to our online customer service team by clicking on the bottom right corner. We’re here to assist you 24/7.
Email:[email protected]

New IEEE Standard – Active. The natural language processing (NLP) services using machine learning have rich applications in solving various tasks and have been widely deployed and used, usually accessible by application programming interface (API) calls. The robustness of the NLP services is challenged by various well-known general corruptions and adversarial attacks. Inadvertent or random deletion, addition, or repetition of characters or words are examples of general corruptions. Adversarial characters, words, or sentence samples are generated by adversarial attacks, causing the models underpinning the NLP services to produce incorrect results. A method for quantitatively evaluating the robustness the NLP services is proposed by this standard. Under the method, different cases the evaluation needs to perform against are specified. Robustness metrics and their calculation are defined. With the standard, understanding of the robustness of the services can be developed by the service stakeholders including the service developer, service providers, and service users. The evaluation can be performed during various phases in the life cycle of the NLP services, the testing phase, in the validation phase, after deployment, and so forth.

PDF Catalog

PDF Pages PDF Title
1 IEEE Std 3168™-2024 Front cover
2 Title page
4 Important Notices and Disclaimers Concerning IEEE Standards Documents
8 Participants
9 Introduction
10 Contents
11 1. Overview
1.1 Scope
1.2 Purpose
1.3 Word usage
12 2. Normative references
3. Definitions, acronyms, and abbreviations
3.1 Definitions
3.2 Acronyms and abbreviations
13 4. Evaluation target
5. Evaluation cases for NLP services
5.1 Overview of evaluation cases
14 5.2 General corruptions
15 5.3 Adversarial attacks
6. Robustness metrics of NLP services
6.1 Metrics overview
16 6.2 Utility metrics
6.3 Corruption resistant metrics
6.4 Adversarial resistant metrics
17 6.5 Quality metrics
6.6 Metrics calculation for NLP services
24 7. Test cases
7.1 Test cases for utility metrics
25 7.2 Test cases for general corruption
7.3 Test cases for adversarial attacks
27 Annex A (Informative) Defense against adversarial attacks
28 Annex B (Informative) Bibliography
29 Back cover
IEEE 3168-2024
$23.33