本文基于以边缘为中心的认知物联网，提出了一种基于边缘计算的FP-gro

Based on the edge-centric cognitive Internet of Things, this paper proposes an edge computing-based FP-growth algorithm detection scheme to resist collusion SSDF attacks. This method can use the BIRCH algorithm to divide all IoT devices into several sub-clusters, execute the FP-growth algorithm in S-FC to identify C-MIDs and filter their perception reports, and finally only send the perception data of NIDs to FC for data fusion . We propose to put the FP-growth algorithm that recognizes C-MIDs into S-FC for execution, which can effectively reduce the pressure of FC to process a large amount of sensing data and speed up the operation of the algorithm. In the simulation experiment, we studied the performance parameters of the detection rate, false alarm rate and false detection rate as the proportion of MIDs increases under three different collusion attacks. The proposed scheme can achieve better performance compared with traditional methods. . In addition, the FP-growth algorithm can reduce the number of scans of the data set. The simulation results show that the algorithm has greatly improved operating efficiency compared with the association rule mining algorithm, and it is suitable as a detection algorithm for edge-level devices. In the future, we will further study the security issues in the cognitive Internet of Things to defend against SSDF attacks in the cognitive Internet of Things.

Based on the edge centered cognitive Internet of things, this paper proposes a FP growth algorithm detection scheme based on edge computing to resist collusive SSDF attacks. This method can use birch algorithm to divide all IOT devices into several sub clusters, execute FP growth algorithm in s-fc to identify c-mids and filter its perception report, and finally only send the perception data of NIDS to FC for data fusion. We propose to put the FP growth algorithm for identifying c-mids into s-fc for execution, which can effectively reduce the pressure of FC processing a large number of perceptual data and speed up the running speed of the algorithm. In the simulation experiment, we study the performance parameters of detection rate, false alarm rate and false detection rate with the increase of the proportion of mids under three different collusion attacks. Compared with the traditional methods, the proposed scheme can obtain better performance. In addition, FP growth algorithm can reduce the number of scanning data sets. The simulation results show that the operation efficiency of FP growth algorithm is greatly improved compared with association rule mining algorithm, and it is suitable for edge layer equipment detection algorithm. In the future, we will further study the security problems in the cognitive Internet of things and defend against SSDF attacks in the cognitive Internet of things.

Based on the edge-centered cognitive Internet of Things, this paper proposes a FP-growth algorithm detection scheme based on edge computing to resist the collusion SSDF attack. This method can use BIRCH algorithm to divide all IoT devices into several sub-clusters, execute FP-growth algorithm in S-FC to identify C-MIDs and filter its perception report, and finally only send the perception data of NIDs to FC for data fusion. We propose to put FP-growth algorithm for identifying C-MIDs into S-FC for execution, which can effectively reduce the pressure of FC to process a large number of perceived data and speed up the algorithm. In the simulation experiment, we study the performance parameters of three different collusion attacks, which change with the increase of the ratio of MIDs, false alarm rate and false detection rate. Compared with the traditional methods, the proposed schemes can achieve better performance. In addition, FP-growth algorithm can reduce the number of scanning data sets, and the simulation results show that compared with association rule mining algorithm, FP-growth algorithm can greatly improve the running efficiency, which is suitable for the detection algorithm of edge layer devices. In the future, we will further study the security problems in cognitive Internet of Things and defend against SSDF attacks in cognitive Internet of Things.