Abstract: Embodiments of this specification provide methods and apparatuses for performing model ownership verification based on an exogenous feature. An implementation of the methods includes: selecting initial samples from an initial sample set to form a selected sample set, processing sample data of the initial samples to obtain transform samples that form a transform sample set, training a meta-classifier based on a target model, an auxiliary model, and the transform sample set, inputting data associated with a suspicious model into the meta-classifier, and determining, based on an output result of the meta-classifier, whether the suspicious model is stolen from a deployment model, wherein the deployment model has feature knowledge of the exogenous feature.

Abstract: The present invention belongs to the technical field of biomass carbon materials, and relates to a lignin porous carbon nanosheet, a preparation method therefor, and an application thereof in supercapacitor electrode materials. The method of the present invention performs layer-by-layer self-assembly of sulfonated lignin and oxalate in a selective solvent to prepare a layer-by-layer self-assembled lignin/oxalate composite, which is then carbonized and pickled to obtain the lignin porous carbon nanosheets. The lignin porous carbon nanosheets prepared by the above method of the present invention have a specific surface area of 200-1500 m2/g, a micropore specific surface area of 100-500 m2/g, a mesoporous specific surface area of 100-1000 m2/g, a pore diameter of 0.5-30 nm, and a pore volume of 0.5-1.5 cm3/g; they can be applied to supercapacitor electrode materials, showing higher specific capacitance and excellent rate performance (with a specific capacitance retention rate of 76.

Abstract: Embodiments of the present specification provide a method, apparatus, and electronic device for preventing model theft during classification using a service classification model. The service classification model is a deep neural network for predicting a category of a service object, including an input layer, multiple intermediate layers, and an output layer that are sequentially stacked.

Abstract: Embodiments of the present specification provide a method, apparatus, and electronic device for preventing model theft during classification using a service classification model. The service classification model is a deep neural network for predicting a category of a service object, including an input layer, multiple intermediate layers, and an output layer that are sequentially stacked.