Zero-trust dynamic identity verification and authorization method based on artificial intelligence

• Main Authors: SHENG YOUGAO, JIN PENG, ZHOU JUN, DONG ZHENJIANG, ZHOU QINGSONG, QI JIN, ZHOU JIN, ZHOU QIHANG, XU QIN, CHENG FEI, YANG ZHENG, SHEN WENWU
• Format: Patent
• Language: Chinese; English
• Published: 12.03.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The invention relates to the field of network security, and discloses a zero-trust dynamic identity verification and authorization method based on artificial intelligence, which comprises the following steps of: S1, acquiring related data of all user behaviors and system states, including basic login information, user behavior data and system state information; s2, establishing a user behavior model based on deep learning, and capturing a time pattern of user behaviors and detecting possible abnormal behaviors of a user by adopting a mode of combining a long short-term memory network and an auto-encoder; s3, according to a result of the step S2, performing dynamic user identity verification and authorization by using a dual deep Q network as a policy decision mechanism, and controlling access of a user to system resources; and S4, monitoring and recording the behaviors of the system and the response of the user to the behaviors of the system, collecting various types of feedback information, and continuously