A Modified PointNet-Based DDoS Attack Classification and Segmentation in Blockchain

With the rapid development of blockchain technology,the number of distributed applications continues to increase,so ensuring the security of the network has become particularly important.However,due to its decentralized,decentralized nature,blockchain networks are vulnerable to distributed denial-of-service(DDoS)attacks,which can lead to service stops,causing serious economic losses and social impacts.The research questions in this paper mainly include two aspects:first,the classification of DDoS,which refers to detecting whether blockchain nodes are suffering DDoS attacks,that is,detecting the data of nodes in parallel;The second is the problem of DDoS segmentation,that is,multiple pieces of data that appear at the same time are determined which type of DDoS attack they belong to.In order to solve these problems,this paper proposes a modified PointNet(MPointNet)for the classification and type segmentation of DDoS attacks.A dataset containing multiple DDoS attack types was constructed using the CIC-DDoS2019 dataset,and trained,validated,and tested accordingly.The results show that the proposed DDoS attack classification method has high performance and can be used for the actual blockchain security maintenance process.The accuracy rate of classification tasks reached 99.65%,and the accuracy of type segmentation tasks reached 85.47%.Therefore,the method proposed in this paper has high application value in detecting the classification and segmentation of DDoS attacks.

Multitask Learning with Multiscale Residual Attention for Brain Tumor Segmentation and Classification

Automatic segmentation and classification of brain tumors are of great importance to clinical treatment.However,they are challenging due to the varied and small morphology of the tumors.In this paper,we propose a multitask multiscale residual attention network(MMRAN)to simultaneously solve the problem of accurately segmenting and classifying brain tumors.The proposed MMRAN is based on U-Net,and a parallel branch is added at the end of the encoder as the classification network.First,we propose a novel multiscale residual attention module(MRAM)that can aggregate contextual features and combine channel attention and spatial attention better and add it to the shared parameter layer of MMRAN.Second,we propose a method of dynamic weight training that can improve model performance while minimizing the need for multiple experiments to determine the optimal weights for each task.Finally,prior knowledge of brain tumors is added to the postprocessing of segmented images to further improve the segmentation accuracy.We evaluated MMRAN on a brain tumor data set containing meningioma,glioma,and pituitary tumors.In terms of segmentation performance,our method achieves Dice,Hausdorff distance(HD),mean intersection over union(MIoU),and mean pixel accuracy(MPA)values of 80.03%,6.649 mm,84.38%,and 89.41%,respectively.In terms of classification performance,our method achieves accuracy,recall,precision,and F1-score of 89.87%,90.44%,88.56%,and 89.49%,respectively.Compared with other networks,MMRAN performs better in segmentation and classification,which significantly aids medical professionals in brain tumor management.The code and data set are available at https://github.com/linkenfaqiu/MMRAN.

Recognition results classification and post-processing methods for painted characters on billet surface

Automatic identification of characters marked on billets is very important for steelworks to achieve manu- facturing and logistics informatization management. Due to the presence of adhesions, fractures, blurs, and other problems in characters painted on billets, character recognition accuracy with machine vision is relatively low, and hardly meets practical application requirements. To make the character recognition results more reliable and accu- rate, an identification results classification and post-pro- cessing method has been proposed in this paper. By analyzing issues in the image segmentation and recognition stage, the recognition result classification model, based on character encoding rules and recognition confidence, is built, and the character recognition results can be classified as correct, suspect, or wrong. In the post-processing stage, a human-machine-cooperation mechanism with a post- processing interface is designed to eliminate error infor- mation in suspect and wrong types. The system was developed and experiments conducted with images acquired in an iron and steel factory. The results show the character recognition accuracy to be approximately 89% using the character recognizer. However, this result cannot be directly applied in information management systems. With the proposed post-processing method, a human worker will query the suspect and wrong results classified by the system, determine whether the result is correct or wrong, and then, correct the wrong result through the post-processing interface. Using this method, the character recognition accuracy ultimately improves to 99.4%. Thus, the results will be more reliable applied in a practical system.