Singapore has put forward a new international standard (ISO/IEC AWI TS 42119-8) (“Testing Standard“) to standardise the testing methodology for Generative Artificial Intelligence (“GenAI“) systems, aimed at strengthening the foundation for trustworthy Artificial Intelligence (“AI“) testing. This is the first international standard of its kind for the testing of GenAI systems.
With the rapid development and pervasiveness of AI across ecosystems, it is crucial that there are globally recognised AI standards to ensure AI is used in a reliable and safe way. Specifically, Singapore has put forth the new Testing Standard with a focus on benchmarking and red teaming methodologies for GenAI systems with standardised testing approaches. Overall, it establishes an important framework for AI testing that enhances the reproducibility and comparability of results. This, in turn, will drive assurance and overall trust in AI systems and enable safer, more reliable adoption by AI deployers and users.
The Testing Standard builds on the Infocomm Media Development Authority’s (“IMDA’s“) past work in developing domestic testing frameworks, including the AI Verify Toolkit and the Starter Kit for Testing of LLM-Based Applications for Safety and Reliability and in the nascent field of assurance through the Global AI Assurance Sandbox. It is part of Singapore’s broader commitment to international AI standards, as seen in the national adoption and accreditation programme of ISO/IEC 42001 led by EnterpriseSG, and the contribution of real-world use cases to support ISO/IEC TR 24030’s documentation of AI applications in practice. Together, these efforts lay the groundwork for trustworthy AI implementation.
Click on the following link for more information:
- IMDA Press Release titled “Singapore Champions New Global AI Testing Standardisation Efforts on Benchmarking and Red Teaming” (available on the IMDA website at www.imda.gov.sg)