DesignationISO/IEC FDIS 24029-3
Stage50.00, FDIS registered
Planning date, an estimate16 Feb 2027
Text todayPublic record and DIS view
Home / The clause register
The clause register
Every unit the public record carries, and the line where it stops.
10 pages in this group. Every page states its citation, the evidence a reviewer asks for, and what it does not cover. Last updated: 2026-10-21.
Clause 1, Scope
The stated subject is a method for applying statistical techniques to judge how robust a neural network is. It covers picking those techniques, running them and keeping them under control. I
Clause 2, Normative references
Three documents are normative: 22989:2022 for vocabulary, 23053:2022 for the machine-learning system model, and 24029-2:2023 for the formal-method companion. A dated reference applies in the
Clause 3, Terms and definitions
The terms and definitions in ISO/IEC 22989:2022 and ISO/IEC 23053:2022 apply, together with the terms the document defines itself. The public view shows one of those terms, stability at 3.1,
Clause 3.1, Stability
Stability is defined as the property that lets an AI system give the same output when its input is perturbed in ways the team has stated in advance. The subject is the whole system, the effe
Clause 4, Abbreviated terms
The clause is titled Abbreviated terms. Its list of abbreviations is withheld. A buyer can still prepare the abbreviation register the clause implies, and align it with the vocabulary in 229
Clause 5, Robustness assessment during the life cycle
The public titles set out a nine-stage life cycle: summary, inception, design and development, verification and validation, deployment, operation and monitoring, continuous validation, re-ev
Clause 6, Robustness properties measurable using statistical methods
The public titles name four topics: general, in-domain robustness assessment, specification of expected behaviour, and other considerations that contribute to robustness assessment. The body
Clause 7, Statistical measures of robust behaviour
The public titles name five measure families beside the general clause: performance drops, the system's response to a targeted perturbation, separability metrics, statistical reliability eng
Clause 8, Selecting datasets representative of a robustness dimension
The public titles cover the general case, the datasets needed for a robustness assessment, the acquisition of data, and the measurement of adversarial robustness. The body text is withheld.
The clauses the public view does not carry
The clause map is public: the table of contents lists clauses 1 to 8.4, with titles. What is withheld is the body text from clause 4 onward, and the text of 3.2 and later terms. The document
The public clause map
Every title the public DIS table of contents lists, clause by clause. The body text under clauses 4 to 8.4 is withheld; the titles are public and are useful on their own. The FDIS may change a title or add a clause when it publishes.
| Clause | Public title | Body |
|---|---|---|
| 1 | Scope | Public |
| 2 | Normative references | Public |
| 3 | Terms and definitions | Public |
| 4 | Abbreviated terms | Withheld |
| 5 | Robustness assessment during the life cycle | Withheld |
| 5.1 | Summary | Withheld |
| 5.2 | Inception | Withheld |
| 5.3 | Design and development | Withheld |
| 5.4 | Verification and validation | Withheld |
| 5.5 | Deployment | Withheld |
| 5.6 | Operation and monitoring | Withheld |
| 5.7 | Continuous validation | Withheld |
| 5.8 | Re-evaluation | Withheld |
| 5.9 | Retirement | Withheld |
| 6 | Robustness properties measurable using statistical methods | Withheld |
| 6.1 | General | Withheld |
| 6.2 | In-domain robustness assessment | Withheld |
| 6.3 | Specification of expected behaviour | Withheld |
| 6.4 | Other considerations that contribute to robustness assessment | Withheld |
| 7 | Statistical measures of robust behaviour | Withheld |
| 7.1 | General | Withheld |
| 7.2 | Robustness assessment based on performance drops | Withheld |
| 7.3 | Targeted assessment of the system's response to a perturbation | Withheld |
| 7.4 | Assessment through separability metrics | Withheld |
| 7.5 | Assessment through statistical reliability engineering | Withheld |
| 7.6 | Robustness assessment through curvature analysis | Withheld |
| 8 | Selection of datasets representative of a robustness dimension | Withheld |
| 8.1 | General | Withheld |
| 8.2 | Datasets needed for robustness assessment | Withheld |
| 8.3 | Acquisition of data for robustness assessment | Withheld |
| 8.4 | Measuring adversarial robustness | Withheld |