Global Markets
Home›Global Markets›Trade & Tariffs›China starts building AI safety benchmark for generati…
China starts building AI safety benchmark for generative models
Applications are due Tuesday for a MIIT-led effort to set a standardized testing platform covering six AI safety dimensions and 31 specific risks.
China’s Ministry of Industry and Information Technology has begun work on a safety benchmark to evaluate artificial intelligence models, as regulators in the United States and Europe step up scrutiny of AI security, according to SCMP Economy.
The MIIT-led National Industrial Information Security Development Research Centre is recruiting companies and experts to help co-build the benchmark, with applications due Tuesday, the outlet said.
The institute said existing AI safety frameworks do not adequately address complex safety and governance needs, and it aims to create a standardized testing platform to support industrial compliance.
The benchmark will assess generative AI across six core dimensions: content safety, value alignment, robustness, fairness, privacy protection, and trustworthiness, using a hybrid methodology designed to cover 31 specific safety risks across five major categories, SCMP Economy reported.