SINGAPORE AI SAFETY INSTITUTE

The Singapore AI Safety Institute (AISI) will drive Singapore’s AI evaluation and testing work, to support addressing gaps in global AI safety sciences.

It is crucial for the state of sciences for safety and governance to keep in tandem with AI’s rapidly evolving capabilities and risks. As the designated Singapore AISI, the Digital Trust Centre Singapore (DTC), in partnership with the Infocomm Media Development Authority of Singapore (IMDA), will drive the efforts for advancing AI safety in Singapore.

About Us

Resources

Testing AI Agents for Data Leakage Risks in Realistic Tasks

Korea and Singapore AISIs jointly tested how AI agents behave in real-world tasks. The exercise examined whether agents can complete multi-step tasks in common settings such as customer service and enterprise productivity without leaking sensitive data. This blogpost shares the key findings, evaluation challenges, and methodological learnings.

Evaluation Report on “Improving Methodologies for LLM Evaluations Across Global Languages”

Following the blogpost released earlier this year, this evaluation report takes a closer look at the various methodological components and findings behind this joint testing exercise, which aims to seed a common approach for multilingual safety testing of frontier models at scale.

Advancing Methodologies for Agentic Evaluations Across Domains

The 3rd Joint Testing Exercise builds on the insights from the previous two exercises, to work towards advancing the science of AI agent evaluations and building common best practices for testing AI agents. Bringing their collective technical and linguistic expertise, participating AISIs worked together to conduct testing for sensitive information leak, fraud, and cybersecurity threats.

Evaluation Report on “Advancing Methodologies for Agentic Evaluations Across Domains”

This evaluation report details the various methodological components and findings behind this joint testing exercise, which will work towards advancing the science of AI agent evaluations and building common best practices for testing AI agents.

Improving Methodologies for AI Model Evaluations Across Global Languages

As part of the International Network of AI Safety Institutes’ continued effort to advance the science of AI model evaluations and work towards building common best practices for testing advanced AI systems, Singapore, Japan, and the United Kingdom led the Network’s latest joint testing exercise aimed at improving the efficacy of model evaluations across different languages

Resources