Advanced New Technologies Co., Ltd.

Ling Xie

Lei Wang

Xiaolong Li

Qunshan Huang

Xingyu Chen

Yuehao Wu

Xin Xu

The implementations provide a method and an apparatus for establishing a trusted cluster. The method is used to form a trusted computing cluster by using N trusted computing units, the method including: grouping the N trusted computing units into a plurality of groups; identifying a first trusted computing unit in each group, and causing first trusted computing units in the plurality of groups to each respectively perform inter-unit trust authentication with other trusted computing units in a same group in parallel; performing inter-group trust authentication between/among the plurality of groups in parallel to obtain the N trusted computing units on which trust authentication succeeds; and propagating secret information in the N trusted computing units on which trust authentication succeeds, so that the N trusted computing units obtain the same secret information to form the trusted computing cluster.

Method and apparatus for establishing trusted computing cluster

Encrypted user data are received at a service device from at least one user equipment, and the user data is encrypted in a trusted zone of the at least one user equipment. The encrypted user data then be decrypted in a trust zone of the service device by a first central processing unit (CPU) to obtain decrypted user data. A model is trained by using the decrypted user data to determine a training intermediate value and a training effective representative value, and a determination is made whether the training effective representative value satisfies a specified condition is determined. If so, the trained model is generated based on a model parameter. Otherwise, a model parameter is iterately adjusted and the model is iteratively trained based on an adjusted model parameter until the trained effective representative value satisfies the specified condition.

Data secruity enhancement by model training

Computer-implemented methods, non-transitory, computer-readable media, and computer-implemented systems for determination of anomalous data are provided. In a computer-implemented method, a plurality of data packets is received within a predetermined time period, the plurality of data packets comprising a data structure. A historical distribution of historical data including the data structure as the data packets is determined. The plurality of data packets is compared to the historical distribution to generate a comparison result. If it is determined that data anomaly exists in the plurality of data packets according to the comparison result, an alert indicating the data anomaly is generated.

Method and device for determining data anomaly

Encrypted user data are received at a service device from at least one user equipment, and the user data is encrypted in a trusted zone of the at least one user equipment. The encrypted user data then be decrypted in a trust zone of the service device by a first central processing unit (CPU) to obtain decrypted user data. A model is trained by using the decrypted user data to determine a training intermediate value and a training effective representative value, and a determination is made whether the training effective representative value satisfies a specified condition is determined. If so, the trained model is generated based on a model parameter. Otherwise, a model parameter is literately adjusted and the model is iteratively trained based on an adjusted model parameter until the trained effective representative value satisfies the specified condition.

Growing community of inventors

Hangzhou, China

Ling Xie