Previous studies have shown that deep learning is very effective in detecting known attacks.However,when facing unknown attacks,models such as Deep Neural Networks(DNN)combined with Long Short-Term Memory(LSTM),Convol...Previous studies have shown that deep learning is very effective in detecting known attacks.However,when facing unknown attacks,models such as Deep Neural Networks(DNN)combined with Long Short-Term Memory(LSTM),Convolutional Neural Networks(CNN)combined with LSTM,and so on are built by simple stacking,which has the problems of feature loss,low efficiency,and low accuracy.Therefore,this paper proposes an autonomous detectionmodel for Distributed Denial of Service attacks,Multi-Scale Convolutional Neural Network-Bidirectional Gated Recurrent Units-Single Headed Attention(MSCNN-BiGRU-SHA),which is based on a Multistrategy Integrated Zebra Optimization Algorithm(MI-ZOA).The model undergoes training and testing with the CICDDoS2019 dataset,and its performance is evaluated on a new GINKS2023 dataset.The hyperparameters for Conv_filter and GRU_unit are optimized using the Multi-strategy Integrated Zebra Optimization Algorithm(MIZOA).The experimental results show that the test accuracy of the MSCNN-BiGRU-SHA model based on the MIZOA proposed in this paper is as high as 0.9971 in the CICDDoS 2019 dataset.The evaluation accuracy of the new dataset GINKS2023 created in this paper is 0.9386.Compared to the MSCNN-BiGRU-SHA model based on the Zebra Optimization Algorithm(ZOA),the detection accuracy on the GINKS2023 dataset has improved by 5.81%,precisionhas increasedby 1.35%,the recallhas improvedby 9%,and theF1scorehas increasedby 5.55%.Compared to the MSCNN-BiGRU-SHA models developed using Grid Search,Random Search,and Bayesian Optimization,the MSCNN-BiGRU-SHA model optimized with the MI-ZOA exhibits better performance in terms of accuracy,precision,recall,and F1 score.展开更多
Female cichlid fish living in African great lakes are known to have sensory systems that are adapted to ambient light environments.These sen-sory system adaptations are hypothesized to have influenced the evolution of...Female cichlid fish living in African great lakes are known to have sensory systems that are adapted to ambient light environments.These sen-sory system adaptations are hypothesized to have influenced the evolution of the diverse male nuptial coloration.In rock-dwelling Lake Malawi mbuna cichlids,however,the extent to which ambient light environments influence female sensory systems and potentially associated male nuptial coloration remains unknown.Yet,the ubiquitous blue flank coloration and UV reflection of male mbuna cichlids suggest the potential impacts of the blue-shifted ambient light environment on these cichlid's visual perception and male nuptial coloration in the shallow water depth in Lake Malawi.In the present study,we explored whether and how the sensory bias of females influences intersexual communication in the mbuna cichlid,Metriaclima zebra.A series of choice experiments in various light environments showed that M.zebra females (1)have a pref-erence for the blue-shifted light environment,(2)prefer to interact with males in blue-shifted light environments,(3)do not show a preference between dominant and subordinate males in full-spectrum,long-wavelength filtered,and short-wavelength filtered light environments,and (4)show a"reversed"preference for subordinate males in the UV-filtered light environment.These results suggest that the visual perception of M.zebra females may be biased to the ambient light spectra in their natural habitat by local adaptation and that this sensory bias may influence the evolution of blueand UV reflectivepatterns in male nuptial coloration.展开更多
A novel zebra mutant, zebra-15, derived from the restorer line JinhuilO （Oryza sativa L. ssp. indica） treated by EMS, displayed a distinctive zebra leaf from seedling stage to jointing stage. Its chlorophyll content...A novel zebra mutant, zebra-15, derived from the restorer line JinhuilO （Oryza sativa L. ssp. indica） treated by EMS, displayed a distinctive zebra leaf from seedling stage to jointing stage. Its chlorophyll content decreased （55.4%） and the ratio of Chla/Chlb increased （90.2%） significantly in the yellow part of the zebra-15, compared with the wild type. Net photosynthetic rate and fluorescence kinetic parameters showed that the decrease of chlorophyll content significantly influenced the photosynthetic efficiency of the mutant. Genetic analysis of F2 segregation populations derived from the cross of XinonglA and zebra-15 indicated that the zebra leaf trait is controlled by a single recessive nuclear gene. Ninety-eight out of four hundred and eighty pairs of SSR markers showed the diversity between the XinonglA and the zebra-15, their F2 population was then used for gene mapping. Zebra-15 （Z-15） gene was primarily restricted on the short arm of chromosome 5 by 150 F2 recessive individuals, 19.6 cM from marker RM3322 and 6.0 cM from marker RM6082. Thirty-six SSR markers were newly designed in the restricted location, and the Z-15 was finally located between markers nSSR516 and nSSR502 with the physical region 258 kb by using 1,054 F2 recessive individuals.展开更多
基金supported by Science and Technology Innovation Programfor Postgraduate Students in IDP Subsidized by Fundamental Research Funds for the Central Universities(Project No.ZY20240335)support of the Research Project of the Key Technology of Malicious Code Detection Based on Data Mining in APT Attack(Project No.2022IT173)the Research Project of the Big Data Sensitive Information Supervision Technology Based on Convolutional Neural Network(Project No.2022011033).
文摘Previous studies have shown that deep learning is very effective in detecting known attacks.However,when facing unknown attacks,models such as Deep Neural Networks(DNN)combined with Long Short-Term Memory(LSTM),Convolutional Neural Networks(CNN)combined with LSTM,and so on are built by simple stacking,which has the problems of feature loss,low efficiency,and low accuracy.Therefore,this paper proposes an autonomous detectionmodel for Distributed Denial of Service attacks,Multi-Scale Convolutional Neural Network-Bidirectional Gated Recurrent Units-Single Headed Attention(MSCNN-BiGRU-SHA),which is based on a Multistrategy Integrated Zebra Optimization Algorithm(MI-ZOA).The model undergoes training and testing with the CICDDoS2019 dataset,and its performance is evaluated on a new GINKS2023 dataset.The hyperparameters for Conv_filter and GRU_unit are optimized using the Multi-strategy Integrated Zebra Optimization Algorithm(MIZOA).The experimental results show that the test accuracy of the MSCNN-BiGRU-SHA model based on the MIZOA proposed in this paper is as high as 0.9971 in the CICDDoS 2019 dataset.The evaluation accuracy of the new dataset GINKS2023 created in this paper is 0.9386.Compared to the MSCNN-BiGRU-SHA model based on the Zebra Optimization Algorithm(ZOA),the detection accuracy on the GINKS2023 dataset has improved by 5.81%,precisionhas increasedby 1.35%,the recallhas improvedby 9%,and theF1scorehas increasedby 5.55%.Compared to the MSCNN-BiGRU-SHA models developed using Grid Search,Random Search,and Bayesian Optimization,the MSCNN-BiGRU-SHA model optimized with the MI-ZOA exhibits better performance in terms of accuracy,precision,recall,and F1 score.
文摘Female cichlid fish living in African great lakes are known to have sensory systems that are adapted to ambient light environments.These sen-sory system adaptations are hypothesized to have influenced the evolution of the diverse male nuptial coloration.In rock-dwelling Lake Malawi mbuna cichlids,however,the extent to which ambient light environments influence female sensory systems and potentially associated male nuptial coloration remains unknown.Yet,the ubiquitous blue flank coloration and UV reflection of male mbuna cichlids suggest the potential impacts of the blue-shifted ambient light environment on these cichlid's visual perception and male nuptial coloration in the shallow water depth in Lake Malawi.In the present study,we explored whether and how the sensory bias of females influences intersexual communication in the mbuna cichlid,Metriaclima zebra.A series of choice experiments in various light environments showed that M.zebra females (1)have a pref-erence for the blue-shifted light environment,(2)prefer to interact with males in blue-shifted light environments,(3)do not show a preference between dominant and subordinate males in full-spectrum,long-wavelength filtered,and short-wavelength filtered light environments,and (4)show a"reversed"preference for subordinate males in the UV-filtered light environment.These results suggest that the visual perception of M.zebra females may be biased to the ambient light spectra in their natural habitat by local adaptation and that this sensory bias may influence the evolution of blueand UV reflectivepatterns in male nuptial coloration.
基金funded by the Excellent Youth Foundation Project of Chongqing (No. 2008BA1033)the Fine Animals and Plants Breeding Project of Chongqing (No. 2007AA1019, 2007AA1012 and 2007AB1033)the National Key Technology R&D Program of China (No. 2006BAD01A01)
文摘A novel zebra mutant, zebra-15, derived from the restorer line JinhuilO （Oryza sativa L. ssp. indica） treated by EMS, displayed a distinctive zebra leaf from seedling stage to jointing stage. Its chlorophyll content decreased （55.4%） and the ratio of Chla/Chlb increased （90.2%） significantly in the yellow part of the zebra-15, compared with the wild type. Net photosynthetic rate and fluorescence kinetic parameters showed that the decrease of chlorophyll content significantly influenced the photosynthetic efficiency of the mutant. Genetic analysis of F2 segregation populations derived from the cross of XinonglA and zebra-15 indicated that the zebra leaf trait is controlled by a single recessive nuclear gene. Ninety-eight out of four hundred and eighty pairs of SSR markers showed the diversity between the XinonglA and the zebra-15, their F2 population was then used for gene mapping. Zebra-15 （Z-15） gene was primarily restricted on the short arm of chromosome 5 by 150 F2 recessive individuals, 19.6 cM from marker RM3322 and 6.0 cM from marker RM6082. Thirty-six SSR markers were newly designed in the restricted location, and the Z-15 was finally located between markers nSSR516 and nSSR502 with the physical region 258 kb by using 1,054 F2 recessive individuals.
