China Academy of Information and Communications Technology collaborates with 360 to initiate the development of large-scale model standards, Building a Strong Defense Line for Artificial Intelligence Security

The big model security benchmark testing aims to establish an authoritative Chinese benchmark testing system for big model security in the industry, uphold "Fairness and impartiality, Industrial application, Selection reference" Three major principles, Through scientifically rigorous testing methods, Assessing the Content Security of Large Models, Data Security andTechnology EthicsPerformance in various aspects. This system will cover the correct values, Legal and compliant, Privacy Protection, Civilized and Healthy, AI Autonomy consciousness, etc 27 A multidimensional Chinese evaluation dataset, Provide comprehensive services for the industry, Detailed security performance testing indicators.

As an important research institution in China's information and communication industry, the Institute of Information and Communications Technology, Has a profound research background and rich industry experience in the fields of artificial intelligence and big data, It's domestic ICT The only field that can connect new technology research, Standard development, Experimental verification, An industrial innovation platform that covers the entire chain and link from detection and certification to industrial promotion. Its professional research team, Extensive industry cooperation network and profound industry influence, Provided a solid guarantee for the smooth progress of large-scale model security benchmark testing.

360 The group has been deeply involved in the field of cybersecurity for many years, Global leader in secure big data scale; And as one of the earliest companies in China to lay out large-scale artificial intelligence models, 360 Self developed cognitive general large model -- "360 Smart Brain" Ranked in the top tier of domestic large model capabilities in multiple third-party evaluations, including the benchmark evaluation of Chinese general large models. With profound accumulation and leading strength in digital security and artificial intelligence, 360 We will provide strong technical support for this standard testing work, Practical experience and innovative ideas, Jointly promote the establishment and improvement of a large-scale model security benchmark testing system.

Industry insiders say, This time, the Institute of Information and Communications Technology and 360 Jointly conducting large-scale model security benchmark testing is a strong alliance, Complementary advantages, Not only can it establish an authoritative and fair security assessment standard within the industry, We will further promote the innovation and application of large-scale model technology, Contribute to the steady development of the artificial intelligence industry.