Deep Learning Social Network Access Control Model Based on User Preferences

A deep learning access controlmodel based on user preferences is proposed to address the issue of personal privacy leakage in social networks.Firstly,socialusers andsocialdata entities are extractedfromthe social networkandused to construct homogeneous and heterogeneous graphs.Secondly,a graph neural networkmodel is designed based on user daily social behavior and daily social data to simulate the dissemination and changes of user social preferences and user personal preferences in the social network.Then,high-order neighbor nodes,hidden neighbor nodes,displayed neighbor nodes,and social data nodes are used to update user nodes to expand the depth and breadth of user preferences.Finally,a multi-layer attention network is used to classify user nodes in the homogeneous graph into two classes:allow access and deny access.The fine-grained access control problem in social networks is transformed into a node classification problem in a graph neural network.The model is validated using a dataset and compared with other methods without losing generality.The model improved accuracy by 2.18%compared to the baseline method GraphSAGE,and improved F1 score by 1.45%compared to the baseline method,verifying the effectiveness of the model.

Simultaneously Enhancing Strength, Ductility and Corrosion Resistance of a Martensitic Stainless Steel via Substituting Carbon by Nitrogen

Two martensitic stainless steels of 2Cr12Ni6 type hardened and tempered at 773 K have been studied:the first with 0.2%carbon content and the second with partial replacement of carbon by nitrogen(C0.1N0.1)in the first steel.It is found that the partial substitution of carbon with nitrogen contributed to an increase in ductility and strength of the steel,presumably due to the formation of more dispersive carbonitrides.Meanwhile,the addition of nitrogen suppressed the precipitation of carbonitrides,so that the solid solution strengthening effect of C0.1N0.1 did not decrease significantly after tempering treatment.In addition,the partial replacement of carbon by nitrogen contributed to improved ability against pitting corrosion(PC)in chloride-containing medium(3.5%NaCl at 303 K).The higher resistance to PC of tempered nitrogen-containing steel is apparently due to the lower content of massive carbonitrides,especially the reduced aggregation at grain boundaries.This leads to a lower acidity and aggressiveness of the test solution near the sample surface due to the accumulation of NH4^(+) ammonium ions in it.As a result of nitrogen addition,exception for Cr_(23)C_(6) and VC,Cr_(2)N and(Cr,V)N type precipitates have also been found in C0.1N0.1 steel and this is consistent with the thermodynamic calculation results.In conclusion,substituting carbon by nitrogen in traditional martensitic stainless steel could realize the simultaneous improvement of multiple properties of martensitic stainless steels.This result provides a promising composition optimization route to develop novel martensitic stainless steels.