Singapore AI Safety Hub (SASH)

SASH describes itself as a research and field-building organisation rooted in Singapore S-3606. Its verification work is an international collaboration on inference verification:

• Collaboration. SASH reports launching, with the Oxford Martin AI Governance Initiative and a team of researchers, an international collaboration to build tools that make AI verifiable across borders, and names the Future of Life Institute as another early partner S-1320.
• Confidential network logger. The first project asks whether confidential network loggers can help distinguish inference from training S-1320. SASH describes loggers that copy the traffic leaving a data centre; in its planned next prototype, a random sample of requests goes to a separate cluster that re-runs them and raises an alarm on a mismatch S-1320. See SASH confidential network logger, Network taps and certifiers and Sampled inference recomputation.
• Code. The first prototype's code is public under the MIT licence S-1319.
• Field listing. The AI Futures Project's verification page lists FLI and SASH as building the logger prototype S-1511.