A network intrusion detection system is critical for cyber security against llegitimate attacks.In terms of feature perspectives,network traffic may include a variety of elements such as attack reference,attack type,a...A network intrusion detection system is critical for cyber security against llegitimate attacks.In terms of feature perspectives,network traffic may include a variety of elements such as attack reference,attack type,a subcategory of attack,host information,malicious scripts,etc.In terms of network perspectives,network traffic may contain an imbalanced number of harmful attacks when compared to normal traffic.It is challenging to identify a specific attack due to complex features and data imbalance issues.To address these issues,this paper proposes an Intrusion Detection System using transformer-based transfer learning for Imbalanced Network Traffic(IDS-INT).IDS-INT uses transformer-based transfer learning to learn feature interactions in both network feature representation and imbalanced data.First,detailed information about each type of attack is gathered from network interaction descriptions,which include network nodes,attack type,reference,host information,etc.Second,the transformer-based transfer learning approach is developed to learn detailed feature representation using their semantic anchors.Third,the Synthetic Minority Oversampling Technique(SMOTE)is implemented to balance abnormal traffic and detect minority attacks.Fourth,the Convolution Neural Network(CNN)model is designed to extract deep features from the balanced network traffic.Finally,the hybrid approach of the CNN-Long Short-Term Memory(CNN-LSTM)model is developed to detect different types of attacks from the deep features.Detailed experiments are conducted to test the proposed approach using three standard datasets,i.e.,UNsWNB15,CIC-IDS2017,and NSL-KDD.An explainable AI approach is implemented to interpret the proposed method and develop a trustable model.展开更多
The rhizosphere microbial community is crucial to plant health.Many studies have explored the association between the rhizosphere microbiome and plant disease.However,few studies have focused on root rot in arecanut p...The rhizosphere microbial community is crucial to plant health.Many studies have explored the association between the rhizosphere microbiome and plant disease.However,few studies have focused on root rot in arecanut palm,a disease causing devastating effects and thus resulting in economic losses that considerably affect the development of the arecanut industry.Here,rhizosphere samples were collected from both healthy arecanut palm plants and root-rotted arecanut palm plants,and the microbial communities were analyzed using high-throughput sequencing.The root-rotted samples exhibited distinct microbial community richness,diversity,and composition compared with the healthy samples,which was associated with p H according to the Mantel test.Identified potential plant pathogens,including Proteobacteria,Bacteroidetes,Chytridiomycota,and Mortierellomycota,were significantly enriched in the root-rotted samples.In contrast,potentially beneficial plant microbes,such as Acidobacteria and Gemmatimonadetes,were significantly depleted in the root-rotted samples.Co-occurrence networks were constructed to further identify microbial relationships in the root-rotted samples.These findings revealed ecological imbalance among beneficial bacteria in the root-rotted samples.The present study therefore provides an integrated view of the association between the microbial community and root rot in arecanut palm.展开更多
文摘A network intrusion detection system is critical for cyber security against llegitimate attacks.In terms of feature perspectives,network traffic may include a variety of elements such as attack reference,attack type,a subcategory of attack,host information,malicious scripts,etc.In terms of network perspectives,network traffic may contain an imbalanced number of harmful attacks when compared to normal traffic.It is challenging to identify a specific attack due to complex features and data imbalance issues.To address these issues,this paper proposes an Intrusion Detection System using transformer-based transfer learning for Imbalanced Network Traffic(IDS-INT).IDS-INT uses transformer-based transfer learning to learn feature interactions in both network feature representation and imbalanced data.First,detailed information about each type of attack is gathered from network interaction descriptions,which include network nodes,attack type,reference,host information,etc.Second,the transformer-based transfer learning approach is developed to learn detailed feature representation using their semantic anchors.Third,the Synthetic Minority Oversampling Technique(SMOTE)is implemented to balance abnormal traffic and detect minority attacks.Fourth,the Convolution Neural Network(CNN)model is designed to extract deep features from the balanced network traffic.Finally,the hybrid approach of the CNN-Long Short-Term Memory(CNN-LSTM)model is developed to detect different types of attacks from the deep features.Detailed experiments are conducted to test the proposed approach using three standard datasets,i.e.,UNsWNB15,CIC-IDS2017,and NSL-KDD.An explainable AI approach is implemented to interpret the proposed method and develop a trustable model.
基金supported by the Hainan Major Research Project for Science and TechnologyChina(No.zdkj201817)+4 种基金partly supported by the National Transgenic Major Project of China(No.2019ZX08010-004)the National Natural Science Foundation of China(Nos.31560021,31772887,and 31860676)the Hainan Natural Science Foundation,China(No.319QN161)the Priming Scientific Research Foundation of Hainan UniversityChina(No.KYQD(ZR)1929)。
文摘The rhizosphere microbial community is crucial to plant health.Many studies have explored the association between the rhizosphere microbiome and plant disease.However,few studies have focused on root rot in arecanut palm,a disease causing devastating effects and thus resulting in economic losses that considerably affect the development of the arecanut industry.Here,rhizosphere samples were collected from both healthy arecanut palm plants and root-rotted arecanut palm plants,and the microbial communities were analyzed using high-throughput sequencing.The root-rotted samples exhibited distinct microbial community richness,diversity,and composition compared with the healthy samples,which was associated with p H according to the Mantel test.Identified potential plant pathogens,including Proteobacteria,Bacteroidetes,Chytridiomycota,and Mortierellomycota,were significantly enriched in the root-rotted samples.In contrast,potentially beneficial plant microbes,such as Acidobacteria and Gemmatimonadetes,were significantly depleted in the root-rotted samples.Co-occurrence networks were constructed to further identify microbial relationships in the root-rotted samples.These findings revealed ecological imbalance among beneficial bacteria in the root-rotted samples.The present study therefore provides an integrated view of the association between the microbial community and root rot in arecanut palm.
