On 31 May 2024, at the Asia Tech x Singapore (ATxSG) 2024, Singapore’s Minister for Communications and Information, Mrs Josephine Teo, launched the AI Verify Project Moonshot (“Project Moonshot“), an easy-to-use testing toolkit designed to address security and safety challenges often associated with the use of large language models (“LLMs“). It is one of the world’s first open-sourced tools to bring together red-teaming, benchmarking, and baseline testing in one platform.
Project Moonshot is an open beta that seeks to provide intuitive results of the quality and safety of a model or application in an easily understood manner. It was developed through collaboration with industry partners to ensure that the tool is useful and aligned with industry needs.
Project Moonshot is part of a key drive towards establishing global testing standards. In this regard, AI Verify Foundation and MLCommons, two of the leading AI testing organisations, are cooperating to build a common safety benchmark suite.
The Infocomm Media Development Authority also introduced the following initiatives at the event:
(a) Third party testing and research & development for the first ever practical guide to multilingual and multicultural red teaming for LLMs, which will be released later this year for global use;
(b) Enhancing the AI Verify Toolkit by pursuing greater alignment to emerging standards & sector-specific requirements;
(c) IMDA and Microsoft signing a Memorandum of Understanding to further engagement on content provenance proof of concept and development of related policies and standards; and
(d) The Nanyang Technological University’s (NTU) Digital Trust Centre taking on the role as Singapore’s AI Safety Institute to ensure the safe and responsible use of AI.
Click on the following links for more information:
Available on the IMDA website at www.imda.gov.sg:
Available on the AI Verify Foundation website at aiverifyfoundation.sg:
