GB/T 45654-2025: Basic security requirements for generative AI services (voluntary; implemented 2025-11-01)
Training-corpus source and content screening, model-safety requirements and the evaluation methods that underpin the security assessment
AIGE-OBL-CN-GBT45654. Drawn from chapter 08.
Text alternative
- Clause: GB/T 45654, GB/T 45654-2025.
- Duty holder: Not stated.
- Applies from: 2025-11-01, Voluntary.
- Artefact: Corpus-screening record.
- Layers: Layer 03, Layer 05.
- Evidence record: Evidence record v1.
- Record schema: Evidence record.
- The same topic in 22 other frameworks; the crosswalk section below links each clause.
Data table: the dates
| Date | Step | Detail |
|---|---|---|
| 2025-11-01 | Voluntary | Recommended (voluntary) national standard; implemented 2025-11-01 |
- Id
AIGE-OBL-CN-GBT45654- Instrument
- GB/T 45654-2025 Basic security requirements for generative AI services standard
- Clause
- GB/T 45654-2025
- Applies from
- Voluntary · Recommended (voluntary) national standard; implemented 2025-11-01
The artefact that evidences it
Corpus-screening record; eval question banks; security-assessment report.
Data table: every relation
| Family | Item | Relation |
|---|---|---|
| Same crosswalk topic | AI Verify 8.1.1, 8.2.1, 1.1.6, 1.7.2, 1.1.1, 4.1.1, 6.1.1, 5.2.1, 5.9.1 | Core clause |
| Same crosswalk topic | CSA AICM DSP-20, DSP-21, MDS-03, MDS-04, MDS-06, MDS-07, AIS-05 | Core clause |
| Same crosswalk topic | China AI Labelling Label Art. 4, Label Art. 5 | Core clause |
| Same crosswalk topic | China Deep Synthesis DeepSyn Art. 14, DeepSyn Art. 16, DeepSyn Art. 17, DeepSyn Art. 15, DeepSyn Art. 20 | Core clause |
| Same crosswalk topic | China GenAI Measures GenAI Art. 7, GenAI Art. 8, GenAI Art. 11, GenAI Art. 12, GenAI Art. 19, GenAI Art. 17 | Core clause |
| Same crosswalk topic | CoE Convention CoE Art. 14(2), CoE Art. 15(2), CoE Art. 16(2)(g) | Core clause |
| Same crosswalk topic | EU AI Act Art. 10, Art. 10(2)(f)–(g), Art. 4a, Art. 53, Art. 53(1)(c), Art. 5(1)(e), Art. 11, Art. 13, Art. 50, Art. 86, Art. 18, Art. 43, Art. 53(1)(d), Art. 50(2), 50(4), Art. 15, Art. 55, Art. 60, Art. 15(3), Art. 9, Art. 42(3) | Core clause |
| Same crosswalk topic | G7 Code G7 Action 3, G7 Action 1 | Core clause |
| Same crosswalk topic | GAO AI Accountability 2.1, 2.2, 2.4, 2.5, 1.9, 3.5, 1.7, 3.7, 3.2 | Core clause |
| Same crosswalk topic | GDPR Art. 5(1)(c), Art. 25, Art. 9, Arts. 13–14, Art. 30, Art. 32 | Core clause |
| Same crosswalk topic | GPAI Code Copyright 1.1–1.5, Transparency 1.1, Transparency 1.2, Safety 3.2, Safety C6 | Core clause |
| Same crosswalk topic | ISO 42001 A.7, A.7.3, A.4, 7.5, A.6, A.8, 9.1 | Core clause |
| Same crosswalk topic | Korea AI Act Art. 31, Art. 34(1)(2), Art. 32(1) | Core clause |
| Same crosswalk topic | NIST AI RMF MAP 2, MEASURE 2.10, MEASURE 2.11, MAP 1, MEASURE 2.8, MAP 1.6, MEASURE 2.9, MEASURE 2, MEASURE 2.7, MEASURE 2.1, MEASURE 1 | Core clause |
| Same crosswalk topic | OECD AI Principles OECD 1.3, OECD 1.4 | Core clause |
| Same crosswalk topic | Singapore Agentic Agentic 2.3.2 | Core clause |
| Same crosswalk topic | Singapore GenAI GenAI 2, GenAI 3, GenAI 5, GenAI 6 | Core clause |
| Same crosswalk topic | TC260 Framework 3.0 TC260 2.1.3, TC260 5.1, TC260 3, TC260 App. 2 II.6, TC260 5.3.14 | Core clause |
| Same crosswalk topic | UK ATRS ATRS 2.4.3, ATRS Tier 1, ATRS 2.2 | Core clause |
| Same crosswalk topic | China Algo. Rec. AlgoRec Art. 16 | Related clause |
| Same crosswalk topic | OWASP Agentic ASI05 | Related clause |
| Same crosswalk topic | OWASP LLM LLM05:2026, LLM01:2026 | Related clause |
Patterns that build it
No pattern in the catalogue names this clause on its "Maps to" line yet; the artefact above is the engineering answer.
The same topic in other frameworks
From the topic crosswalk: the clauses filed under the same topics as this one. Mappings are illustrative, not a claim of conformity.
Data governance
- EU AI Act Art. 10 Data and data governance (core)
- ISO 42001 A.7 Data for AI systems (core)
- TC260 Framework 3.0 TC260 2.1.3 Data safety risks (core)
- China GenAI Measures GenAI Art. 7 Training-data lawful sourcing (core)
- China GenAI Measures GenAI Art. 8 Data-annotation standards (core)
- China GenAI Measures GenAI Art. 11 Protection of user input and records (core)
- China Deep Synthesis DeepSyn Art. 14 Training-data management (core)
- EU AI Act Art. 10(2)(f)–(g) Examination for possible biases; measures to detect, prevent and mitigate them (core)
- GDPR Art. 5(1)(c) Data minimisation (core)
- GDPR Art. 25 Data protection by design and by default (core)
- ISO 42001 A.7.3 Acquisition of data (core) (clause not verified)
- CSA AICM DSP-20 Data Provenance and Transparency (core)
- UK ATRS ATRS 2.4.3 Development data specification (core)
- Singapore GenAI GenAI 2 Data (core)
- GAO AI Accountability 2.1 Sources: document sources and origins of data used to develop the models (core)
- GAO AI Accountability 2.2 Reliability: assess reliability of data used to develop the models (core)
- AI Verify 8.1.1 Data Governance: put in place measures to ensure data quality over time (core)
- AI Verify 8.2.1 Data Governance: understand the lineage of data (origin, collection, curation, movement) through a data provenance record (core)
- EU AI Act Art. 4a Special-category data for bias detection
- ISO 42001 A.4 Resources for AI systems
- NIST AI RMF MAP 2 MAP 2: Categorization of the AI system is performed
- NIST AI RMF MEASURE 2.10 MEASURE 2.10: Privacy risk of the AI system is examined and documented
- NIST AI RMF MEASURE 2.11 MEASURE 2.11: Fairness and bias are evaluated and results are documented
- TC260 Framework 3.0 TC260 5.1 Model R&D safety guidelines
- EU AI Act Art. 53 Obligations for providers of general-purpose AI models
- EU AI Act Art. 53(1)(c) Copyright policy, including rights reservations
- EU AI Act Art. 5(1)(e) Prohibited: untargeted scraping of facial images
- GPAI Code Copyright 1.1–1.5 Commitment 1: Copyright policy (Measures 1.1 to 1.5)
- GDPR Art. 9 Processing of special categories of personal data
- CSA AICM DSP-21 Data Poisoning Prevention & Detection
- OWASP LLM LLM05:2026 Data and Model Poisoning
- GAO AI Accountability 2.4 Variable selection: assess data variables used in the AI component models
- GAO AI Accountability 2.5 Enhancement: assess the use of synthetic, imputed, and/or augmented data
Documentation and transparency
- EU AI Act Art. 11 Technical documentation (core)
- EU AI Act Art. 13 Transparency and provision of information to deployers (core)
- EU AI Act Art. 53 Obligations for providers of general-purpose AI models (core)
- ISO 42001 7.5 Documented information (core)
- ISO 42001 A.6 AI system life cycle (core)
- ISO 42001 A.8 Information for interested parties (core)
- China AI Labelling Label Art. 4 Explicit labels for generated content (core)
- China AI Labelling Label Art. 5 Implicit (metadata) labels (core)
- China GenAI Measures GenAI Art. 12 Labelling of generated content (core)
- China Deep Synthesis DeepSyn Art. 16 Implicit technical labels (core)
- China Deep Synthesis DeepSyn Art. 17 Conspicuous labels for confusable content (core)
- GPAI Code Transparency 1.1 Drawing up and keeping up-to-date model documentation (core)
- GDPR Arts. 13–14 Information to be provided to the data subject (core)
- CSA AICM MDS-03 Model Documentation (core)
- Korea AI Act Art. 31 Transparency: prior notice, output labelling, realistic synthetic content (core)
- UK ATRS ATRS Tier 1 Summary information (core)
- Singapore GenAI GenAI 3 Trusted Development and Deployment (core)
- CoE Convention CoE Art. 14(2) Documentation sufficient to contest decisions; complaint to authorities (core)
- OECD AI Principles OECD 1.3 Transparency and explainability (core)
- G7 Code G7 Action 3 Publicly report capabilities, limitations and domains of use (core)
- GAO AI Accountability 1.9 Transparency: enable external stakeholders to access information on the design, operation, and limitations of the AI system (core)
- GAO AI Accountability 3.5 Documentation: document the methods for assessment, performance metrics, and outcomes of the AI system (core)
- AI Verify 1.1.6 Transparency: publicly report accuracy, intended use cases, limitations, risk assessment and mitigations to stakeholders (core)
- AI Verify 1.7.2 Transparency: make model or system cards publicly available where warranted by public interest (core)
- EU AI Act Art. 50 Transparency obligations for providers and deployers of certain AI systems
- NIST AI RMF MAP 1 MAP 1: Context is established and understood
- NIST AI RMF MEASURE 2.8 MEASURE 2.8: Risks associated with transparency and accountability are examined and documented
- China GenAI Measures GenAI Art. 19 Disclosure to regulators
- China Algo. Rec. AlgoRec Art. 16 Notice that recommendation is used
- EU AI Act Art. 86 Right to explanation of individual decision-making
- EU AI Act Art. 18 Documentation keeping
- EU AI Act Art. 43 Conformity assessment
- EU AI Act Art. 53(1)(d) Public summary of the content used for training
- EU AI Act Art. 50(2), 50(4) Machine-readable marking of synthetic content; disclosure of deep fakes
- GPAI Code Transparency 1.2 Providing relevant information
- GDPR Art. 30 Records of processing activities
- NIST AI RMF MAP 1.6 MAP 1.6: System requirements are elicited from and understood by relevant AI actors. Design decisions take socio-technical implications into account to address AI risks
- NIST AI RMF MEASURE 2.9 MEASURE 2.9: The AI model is explained, validated, and documented, and AI system output is interpreted within its context as identified in the MAP function to inform responsible use and governance
- CSA AICM MDS-04 Model Documentation Requirements
- Korea AI Act Art. 34(1)(2) Explanation plan: result, main criteria, training-data overview
- UK ATRS ATRS 2.2 Description and rationale
- CoE Convention CoE Art. 15(2) Notification of interaction with an AI system
- GAO AI Accountability 1.7 Specifications: establish and document technical specifications
- AI Verify 1.1.1 Transparency: design an in-house policy on communication to consumers that articulates the principles for transparency
Robustness, security and evaluations
- EU AI Act Art. 15 Accuracy, robustness and cybersecurity (core)
- EU AI Act Art. 55 Obligations for providers of general-purpose AI models with systemic risk (core)
- ISO 42001 A.6 AI system life cycle (core)
- NIST AI RMF MEASURE 2 MEASURE 2: AI systems are evaluated for trustworthy characteristics (core)
- TC260 Framework 3.0 TC260 3 Technological countermeasures (core)
- TC260 Framework 3.0 TC260 App. 2 II.6 Sandbox validation and red teaming (core)
- China Deep Synthesis DeepSyn Art. 15 Technology management and algorithm verification (core)
- China Deep Synthesis DeepSyn Art. 20 Security assessment of new products (core)
- GPAI Code Safety 3.2 Measure 3.2: Model evaluations (core)
- NIST AI RMF MEASURE 2.7 MEASURE 2.7: AI system security and resilience as identified in the MAP function are evaluated and documented (core)
- CSA AICM MDS-06 Adversarial Attack Analysis (core)
- CSA AICM MDS-07 Robustness against Adversarial Attack / Model Hardening (core)
- Singapore GenAI GenAI 5 Testing and Assurance (core)
- Singapore GenAI GenAI 6 Security (core)
- Singapore Agentic Agentic 2.3.2 Before deploying, test agents (core)
- CoE Convention CoE Art. 16(2)(g) Testing before first use and when significantly modified (core)
- OECD AI Principles OECD 1.4 Robustness, security and safety (core)
- G7 Code G7 Action 1 Identify, evaluate and mitigate risks across the lifecycle, including testing (core)
- GAO AI Accountability 3.7 Assessment: assess performance against defined metrics to ensure the AI system functions as intended and is sufficiently robust (core)
- AI Verify 4.1.1 Safety (technical test): run use-case benchmarks and red-teaming to evaluate for safety and possible harms (e.g. hallucination, toxicity) (core)
- AI Verify 6.1.1 Robustness (technical test): compare accuracy with and without added noise to document and monitor performance (core)
- AI Verify 5.2.1 Security: conduct security risk assessments that model threats and risks to the AI system (core)
- EU AI Act Art. 60 Testing of high-risk AI systems in real-world conditions outside AI regulatory sandboxes
- ISO 42001 9.1 Monitoring, measurement, analysis and evaluation
- TC260 Framework 3.0 TC260 5.3.14 Resilience
- China GenAI Measures GenAI Art. 17 Security assessment
- EU AI Act Art. 15(3) Declared accuracy levels and metrics
- EU AI Act Art. 9 Risk management system
- EU AI Act Art. 42(3) Presumption of conformity for cybersecurity (Cyber Resilience Act)
- GPAI Code Safety C6 Commitment 6: Security mitigations
- GDPR Art. 32 Security of processing
- NIST AI RMF MEASURE 2.1 MEASURE 2.1: Test sets, metrics, and details about the tools used during TEVV are documented
- NIST AI RMF MEASURE 1 MEASURE 1: Appropriate methods and metrics are identified and applied
- CSA AICM AIS-05 Application Security Testing
- OWASP LLM LLM01:2026 Prompt Injection
- OWASP Agentic ASI05 Unexpected Code Execution (RCE)
- Korea AI Act Art. 32(1) Safety duties for AI above the compute threshold
- GAO AI Accountability 3.2 Metrics: define performance metrics that are precise, consistent, and reproducible
- AI Verify 5.9.1 Security: release AI systems only after appropriate and effective security checks and evaluation
Source
Chapter 08, section China, checked against its sources on the review date above.
Machine-readable
- This obligation:
/api/v1/obligations/aige-obl-cn-gbt45654.json - The register:
/api/v1/obligations.json· CSV - Schema and stability promise: open data and API
Cite this obligation
García Aibar, J. (2026). GB/T 45654-2025: Basic security requirements for generative AI services (voluntary; implemented 2025-11-01) (AIGE-OBL-CN-GBT45654). In AI Governance Engineering: The Thesis & Body of Knowledge (v0.5.0). https://doi.org/10.5281/zenodo.22956197. https://aigovernanceengineer.com/obligations/aige-obl-cn-gbt45654. CC BY 4.0
BibTeX
@misc{aige2026obligation,
author = {Jorge García Aibar},
title = {{GB/T 45654-2025: Basic security requirements for generative AI services (voluntary; implemented 2025-11-01) (AIGE-OBL-CN-GBT45654)}},
howpublished = {In AI Governance Engineering: The Thesis \& Body of Knowledge},
year = {2026},
version = {0.5.0},
doi = {10.5281/zenodo.22956197},
url = {https://aigovernanceengineer.com/obligations/aige-obl-cn-gbt45654},
note = {Version 0.5.0}
}