Eclipse attacks， as a significant threat to blockchain network layer， can isolate the attacked node from entire network by controlling its network connections， thus affecting its ability to receive block and transaction information. On this basis， attackers can also launch double-spending and other attacks， which causes substantial damage to blockchain system. To address this issue， a dynamic detection method of eclipse attacks for blockchain node analysis was proposed by incorporating deep learning models. Firstly， Node Comprehensive Resilience Index （NCRI） was utilized to represent multidimensional attribute features of the nodes， and Graph ATtention network （GAT） was introduced to update the node features of network topology dynamically. Secondly， Convolutional Neural Network （CNN） was employed to fuse multidimensional features of the nodes. Finally， a Multi-Layer Perceptron （MLP） was used to predict vulnerability of the entire network. Experimental results indicate that an accuracy of up to 89.80% is achieved by the method under varying intensities of eclipse attacks， and that the method maintains stable performance in continuously changing blockchain networks.

Image data in actual business scenarios usually presents the characteristics of rich content and complex distortion performance， which is a great challenge to the generalization of objective Image Quality Assessment （IQA） algorithms. In order to solve this problem， a No-Reference IQA （NR-IQA） algorithm was proposed， which is mainly composed of three sub-networks： Feature Extraction Network （FEN）， Feature Fusion Network （FFN）， and Adaptive Prediction Network （APN）. Firstly， the global view， local patch， and saliency view of the sample were input into the FEN together， and the global distortion， local distortion， and saliency features were extracted by Swim Transformer. Then， the cascaded Transformer encoder was used to fuse the global distortion features and local distortion features， and the potential correlation patterns of the two were explored. Inspired by the human visual attention mechanism， the saliency features were used in the FFN to activate the attention module， so that the module was able to pay additional attention to the visual salient region， so as to improve the semantic parsing ability of the algorithm. Finally， the prediction score was calculated by the dynamically constructed MultiLayer Perceptron （MLP） regression network. Experimental results on main stream synthetic and real-world distortion datasets show that compared with the DSMix （Distortion-induced Sensitivity map-guided Mixed augmentation） algorithm， the proposed algorithm improves the Spearman Rank-order Correlation Coefficient （SRCC） by 4.3% on TID2013 dataset， and the Pearson Linear Correlation Coefficient （PLCC） by 1.4% on KonIQ dataset. The proposed algorithm also demonstrates excellent generalization ability and interpretability， which can deal with the complex distortion performance in business scenarios effectively， and can make adaptive prediction according to the individual characteristics of the sample.

To solve the congestion problem at node in delay tolerant networks, an active congestion control strategy based on historical probability was proposed. The strategy put forward the concept of referenced probability that could be adjusted dynamically by the degree of congestion. Referenced probability would control the forwarding conditions to avoid and control the congestion at node. At the same time the utilization of idle resources and the transmission efficiency of the network would be promoted. The simulation results show that the strategy upgrades delivery ratio of the entire network and reduces the load ratio and message loss rate. As a result, the active congestion control is realized and the transmission performance of the network is enhanced.