Under the background of emphasizing data right confirmation and privacy protection， federated learning， as a new machine learning paradigm， can solve the problem of data island and privacy protection without exposing the data of all participants. Since the modeling methods based on federated learning have become mainstream and achieved good effects at present， it is significant to summarize and analyze the concepts， technologies， applications and challenges of federated learning. Firstly， the development process of machine learning and the inevitability of the appearance of federated learning were elaborated， and the definition and classification of federated learning were given. Secondly， three federated learning methods （including horizontal federated learning， vertical federated learning and federated transfer learning） which were recognized by the industry currently were introduced and analyzed. Thirdly， concerning the privacy protection issue of federated learning， the existing common privacy protection technologies were generalized and summarized. In addition， the recent mainstream open-source frameworks were introduced and compared， and the application scenarios of federated learning were given at the same time. Finally， the challenges and future research directions of federated learning were prospected.

In view of the problem that verifying the conformance of e-government network structure, a conformance verification method for e-government network based on graph approximate matching was proposed. The method firstly abstracted the graph model of e-government network, then used the modular characteristic of network structure and k-hop neighboring relationship of vertices to realize extendible approximate graph matching which got all the similar structures between the two graphs. And then it proposed an improved graph similarity measure function by introducing the node importance factor and path distance attenuation factor so as to make the conformity assessment results more accurate. The experimental result shows that the method can accurately evaluate the conformance degree of e-government network structure, and fine-grainedly reflect the similarities or differences between the network structures which include all kinds of violations in the network topology and system deployment.

In order to improve the efficiency of remote attestation for platform configuration, a method based on RAMT (Remote Attestation based on Merkle Hash Tree) was proposed which improved the approach to storing the Hash value of trusted entities by using a dynamic Huffman tree. And the relevant proof of verification efficiency was also given. From the point of view of data structures used for storing the integrity Hash value of the application software, the problems of the existing methods were analyzed. And detailed description about architecture, measurement and verification of RADHT (Remote Attestation based on a Dynamic Huffman Tree) was given. An example about integrity measurement algorithm was presented for the proposed mechanism. The ability in privacy protection and the efficiency of RADHT were discussed. Compared with RAMT, the probability of the integrity Hash value inquired and its update were considered. Results show the efficiency of the remote attestation is improved.

In the large-scale cloud storage system based on copy redundancy, previous layout algorithm can only partially meet the requirements of high reliability, high scalability and high efficiency in the replica layout. To solve this problem, this paper proposed a Replica Placement algorithm based on Grouping and Consistent Hashing (RPGCH). The storage nodes were classified into different groups by their correlativity, then the replicas of one object were assigned in different groups by consistent hashing algorithm, after that each replica was placed into corresponding storage node in the group by consistent Hashing algorithm. The theoretical analysis proves that the reliability of data is improved. The simulation results show that RPGCH can assign data evenly among storage nodes and adapt well with the changing scale of cloud storage system. Moreover, RPGCH is time efficient with little memory overhead.

The vector digital watermark is one of the most important means of copyright protection for graphics and vector maps. The authors discussed a blind watermarking method for 2D vector map. First, the entire vector map was traversed to get the tolerance dynamically, then the classical Douglas-Peucker algorithm was used to get the entire feature nodes from vector map, and finally, the watermark was embedded into feature nodes in tolerance range. And with the inversed procedure of the embedding process, the watermark could be extracted. Through the attack method including random adding points, random deleting points, compression and cropping, the correlation coefficient of original watermark bits and the extracted watermark bits from attacked watermarked maps were calculated. The experimental results show that the proposed method has a great robustness.

A new strategy of resources distribution based on fuzzy decision making was provided, and a model of multi-objective fuzzy decision making was built to solve the resources distribution problems in grid computing. Also implementation of the strategy was described. Analysis proves that this model not only provides the best resources to tasks, but also enhances the success of matching resources and the efficiency of using resources.