New economy see 丨 Promoting artificial intelligence security and controlling the first -faced industrial scenario full data type AI detection product release 丨 Cover every day

Cover news reporter Zhang Yuexi

At present, artificial intelligence technology has accelerated the evolution and profoundly changes people's production and lifestyle. The follow -up of data privacy, algorithm discrimination, security risks and other parts of artificial intelligence have also attracted common attention from all parties. More urgent requirements for AI security.

On September 1, at the "2022 World Artificial Intelligence Conference" site in Shanghai, China Xintong Institute, Tsinghua University, and Ant Group jointly released the AI ​​security testing platform "Ant Jian". Detect the product.

The reporter learned that the platform is equipped with more than 1,000 trusted AI patents and combines self -developed intelligent game confrontation technology, which can realize automated testing, quantitative scores and security enhancement of different data types such as text, images, tables, and sequences.

According to Li Junkui, president of the Ant Group's Great Security Technology Department, the platform is embedded with the self -developed AI security computing engine, which has improved the computing performance by dozens of times; Black production and automatic evolution attack means, "detection -defense -upgrade" for AI models can effectively discover AI model vulnerabilities and reduce systemic risks. In addition, the platform covers "random noise", "migration" of "random noise", "migration Attack "attack samples are more in line with the attack evaluation benchmark of industrial applications.

Shi Lin, deputy director of the content and technology department of the Institute of Cloud Computing and Big Data of China Xintong Institute, said that artificial intelligence technology is deeply integrated in the fields of manufacturing, medical, energy, transportation, and urban construction, and the issue of AI algorithms is constantly appearing. The problems of algorithm black box, algorithm design defects, data dependencies, confrontation sample attacks and other issues bring great hidden security risks to the industrialized application of intelligent technology. AI is a large -scale application of industrial scenarios. It is necessary to achieve full -link security and credibility, and continue to strengthen model robustness.

Li Qi, an associate professor at Tsinghua University, said that the general automation testing of artificial intelligence algorithms is the core of research and solving artificial intelligence security issues. The AI ​​security testing platform launched this time has first fully solved the systematic and automated evaluation of AI algorithms in different scenarios, and provided a security quantitative evaluation indicators for AI industrial -grade applications, which helps to help artificial intelligence algorithms in the industrial world. Safety guarantees are provided in scale applications.

The reporter learned that on the same day, in addition to the official release of the AI ​​security testing platform "Ant Jian", the unveiling ceremony of the "Trusted AI Joint Laboratory" jointly created by the East China Branch of the China Institute of Information and Communication and Jingdong Exploration Research Institute was also officially held.

The "Trusted AI Joint Lab" will build the method, technical, specifications and tool sets of artificial intelligence algorithms and platform security test evaluation, and establish a systematic and credible assessment specifications around AI application management, AI algorithm models, platform systems and hardware products, etc. , Work together to carry out algorithm model detection and standard research, guide enterprises to participate in the research and development of trusted artificial intelligence, build and improve the AI ​​ecology, accelerate the construction of AI algorithm trusted assessment capabilities, and build an AI application ecosystem.

Relevant person in charge said that promoting artificial intelligence, transparent release, safe and controllable, and diversified tolerance has become a global consensus. The artificial intelligence industry ecosystem that integrates trusted factor will become the only way for artificial intelligence development in the new era.

- END -