Singapore launches generative AI testing toolkit Project Moonshot to address LLM safety and security challenges
25 June 2024
On 31 May 2024, the Info-communications Media Development Authority of Singapore (“IMDA”) issued a press release on the launch of AI Verify 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”), the cornerstone of many AI-driven solutions.
Project Moonshot is one of the world’s first open-sourced tools to bring red-teaming, benchmarking, and baseline testing together in an easy-to-use platform. Released as an open beta on 31 May 2024, Project Moonshot aims to provide intuitive results of the quality and safety of a model or application in an easily understood manner, even for a non-technical user.
Project Moonshot is also part of a move towards global testing standards. The press release reports that two leading AI testing organisations have come together to build a common safety benchmark suite, building on efforts like Project Moonshot.
IMDA is also working with frontier companies to advance third party testing and R&D by developing the first ever practical guide to multi-lingual and multi-cultural red teaming for LLMs. The guide is slated to be released later in 2024 for global use.
Reference materials
The following materials are available on the IMDA website www.imda.gov.sg: