检索结果-南通市图书馆

Fusion of Spiral Convolution-LSTM for Intrusion Detection Modeling

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 2315-2329页

作者： Fei Wang Zhen Dong school of Cyberspace Security Gansu University of Political Science and LawLanzhou73000China

Aiming at the problems of low accuracy and slow convergence speed of current intrusion detection models,SpiralConvolution is combined with Long Short-Term Memory Network to construct a new intrusion detection *** dataset is first preprocessed using solo thermal encoding and normalization *** the spiral convolution-Long Short-Term Memory Network model is constructed,which consists of spiral convolution,a two-layer long short-term memory network,and a *** is shown through experiments that the model is characterized by high accuracy,small model computation,and fast convergence speed relative to previous deep learning *** model uses a new neural network to achieve fast and accurate network traffic intrusion *** model in this paper achieves 0.9706 and 0.8432 accuracy rates on the NSL-KDD dataset and the UNSWNB-15 dataset under five classifications and ten classes,respectively.

关键词： Intrusion detection deep learning spiral convolution long and short term memory networks 1D-spiral convolution

Enhancing Image Description Generation through Deep Reinforcement Learning:Fusing Multiple Visual Features and Reward Mechanisms

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第2期78卷 2469-2489页

作者： Yan Li Qiyuan Wang Kaidi Jia school of Cyber Security Gansu University of Political Science and LawLanzhou730070China

Image description task is the intersection of computer vision and natural language processing,and it has important prospects,including helping computers understand images and obtaining information for the visually *** study presents an innovative approach employing deep reinforcement learning to enhance the accuracy of natural language descriptions of *** method focuses on refining the reward function in deep reinforcement learning,facilitating the generation of precise descriptions by aligning visual and textual features more *** approach comprises three key ***,it utilizes Residual Network 101(ResNet-101)and Faster Region-based Convolutional Neural Network(Faster R-CNN)to extract average and local image features,respectively,followed by the implementation of a dual attention mechanism for intricate feature ***,the Transformer model is engaged to derive contextual semantic features from textual ***,the generation of descriptive text is executed through a two-layer long short-term memory network(LSTM),directed by the value and reward *** with the image description method that relies on deep learning,the score of Bilingual Evaluation Understudy(BLEU-1)is 0.762,which is 1.6%higher,and the score of BLEU-4 is ***-based Image Description Evaluation(CIDEr)scored 0.998,Recall-Oriented Understudy for Gisting Evaluation(ROUGE)scored 0.552,the latter improved by 0.36%.These results not only attest to the viability of our approach but also highlight its superiority in the realm of image *** research can explore the integration of our method with other artificial intelligence(AI)domains,such as emotional AI,to create more nuanced and context-aware systems.

关键词： Image description deep reinforcement learning attention mechanism

A Time Series Intrusion Detection Method Based on SSAE,TCN and Bi-LSTM

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第1期78卷 845-871页

作者： Zhenxiang He Xunxi Wang Chunwei Li school of Cyberspace Security Gansu University of Political Science and LawLanzhou730000China

In the fast-evolving landscape of digital networks,the incidence of network intrusions has escalated ***,the crucial role of time series data in intrusion detection remains largely underappreciated,with most systems failing to capture the time-bound nuances of network *** leads to compromised detection accuracy and overlooked temporal *** this gap,we introduce a novel SSAE-TCN-BiLSTM(STL)model that integrates time series analysis,significantly enhancing detection *** approach reduces feature dimensionalitywith a Stacked Sparse Autoencoder(SSAE)and extracts temporally relevant features through a Temporal Convolutional Network(TCN)and Bidirectional Long Short-term Memory Network(Bi-LSTM).By meticulously adjusting time steps,we underscore the significance of temporal data in bolstering detection *** the UNSW-NB15 dataset,ourmodel achieved an F1-score of 99.49%,Accuracy of 99.43%,Precision of 99.38%,Recall of 99.60%,and an inference time of 4.24 *** the CICDS2017 dataset,we recorded an F1-score of 99.53%,Accuracy of 99.62%,Precision of 99.27%,Recall of 99.79%,and an inference time of 5.72 *** findings not only confirm the STL model’s superior performance but also its operational efficiency,underpinning its significance in real-world cybersecurity scenarios where rapid response is *** contribution represents a significant advance in cybersecurity,proposing a model that excels in accuracy and adaptability to the dynamic nature of network traffic,setting a new benchmark for intrusion detection systems.

关键词： Network intrusion detection bidirectional long short-term memory network time series stacked sparse autoencoder temporal convolutional network time steps

Smart Contract Vulnerability Detection Method Based on Feature Graph and Multiple Attention Mechanisms

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 3023-3045页

作者： Zhenxiang He Zhenyu Zhao Ke Chen Yanlin Liu school of Cyber Security Gansu University of Political Science and LawLanzhou730070China

The fast-paced development of blockchain technology is ***,the security concerns of smart contracts represent a significant challenge to the stability and dependability of the entire blockchain *** smart contract vulnerability detection primarily relies on static analysis tools,which are less efficient and *** deep learning methods have improved detection efficiency,they are unable to fully utilize the static relationships within ***,we have adopted the advantages of the above two methods,combining feature extraction mode of tools with deep learning ***,we have constructed corresponding feature extraction mode for different vulnerabilities,which are used to extract feature graphs from the source code of smart ***,the node features in feature graphs are fed into a graph convolutional neural network for training,and the edge features are processed using a method that combines attentionmechanismwith gated ***,the revised node features and edge features are concatenated through amulti-head *** result of the splicing is a global representation of the entire feature *** method was tested on three types of data:Timestamp vulnerabilities,reentrancy vulnerabilities,and access control vulnerabilities,where the F1 score of our method reaches 84.63%,92.55%,and 61.36%.The results indicate that our method surpasses most others in detecting smart contract vulnerabilities.

关键词： Blockchain smart contracts deep learning graph neural networks

The Binary Logic of the Compilation of the Ecological Environment Code and Its Unfolding

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Social Sciences in China 2024年第3期45卷 76-94页

作者： Dou Xiaodong Guanghua law school Zhejiang University

The Ecological Environment Code,as a significant legal instrument for the evolution of ecological civilization,possesses both substantive and formal ***,it aims to serve the national ecological civilization ***,it elucidates potential pathways for legal interpretation,development of legal rules,and promotion of judicial governance,restraining arbitrary behavior and disorder while facilitating systemic *** compilation of the Ecological Environment Code unfolds through the main threads of substantive and formal *** prioritizing conservation,protection,and restoring the natural environment,resource management,pollution prevention,and ecological protection are coordinated,integrating legislation on ecological protection with management of natural resources and pollution prevention to achieve both"harm avoidance"and"beneficial trends."Employing the formal logical main thread of the structure of the relationship between power and rights,we present four types of norms:ex post facto remedy,hazard prevention,risk prevention,and independent value selection.

关键词： compilation of the Ecological Environment Code binary logic main thread of formal logic main thread of substantive logic

Establishing a mechanism for international cooperation for Fukushima nuclear-contaminated water monitoring

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Population,Resources and Environment 2024年第1期22卷 20-33页

作者： Shumei Yue Xiaodi Yang school of International law Southwest University of Political Science&LawChongqing 401120China

The Japanese government’s unilateral decision to discharge the nuclear-contaminated water from the Fukushima nuclear power plant into the ocean has caused immense nuclear safety *** the unclear contaminated water is a starting point to combat these risks and seek remedies for the rights and interests of all concerned *** establishment of a mechanism for international cooperation in this respect is necessary to handle the risks of the Fukushima nuclear-contaminated water and to lay the foundation of a framework for tackling any future disposal of nuclear-contaminated water following Japan’s *** present,the international legal systems in the spheres of nuclear safety and security,marine environmental protection,and other areas,as well as the questioning of the monitoring reports of the International Atomic Energy Agency(IAEA)by the relevant parties,the monitoring practices of historical nuclear accidents,and numerous radioactivity monitoring mechanisms have provided the institutional and practical basis for constructing such a *** mechanism can be promoted by the IAEA through its existing mechanisms or be jointly initiated by China,the Russian Federation,the Republic of Korea,the Democratic People’s Republic of Korea,and the Pacific Island countries,among other ***,this mechanism should consist of three levels:first,the framework of the basic legal system,including the cooperative principles of national sovereignty,interest-relatedness,and procedural fairness,and the signing of the Framework Convention on the Monitoring of Fukushima’s nuclear-contaminated water and its Optional Protocol;second,the organizational structure and its responsibilities,which may include the Conference of Parties as the decision-making body,the Secretariat as the central coordinating body,and the monitoring committees in various fields as specific implementing agencies;and third,specific administrative arrangements,which involve the

关键词： Nuclear safety Fukushima nuclear-contaminated water Nuclear-contaminated water monitoring Mechanism for international cooperation

High-dimensional robust inference for censored linear models

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Science China Mathematics 2024年第4期67卷 891-918页

作者： Jiayu Huang Yuanshan Wu school of Mathematics and Statistics Wuhan UniversityWuhan 430072China school of Statistics and Mathematics Zhongnan University of Economics and LawWuhan 430073China

Due to the direct statistical interpretation,censored linear regression offers a valuable complement to the Cox proportional hazards regression in survival *** propose a rank-based high-dimensional inference for censored linear regression without imposing any moment condition on the model *** develop a theory of the high-dimensional U-statistic,circumvent challenges stemming from the non-smoothness of the loss function,and establish the convergence rate of the regularized estimator and the asymptotic normality of the resulting de-biased estimator as well as the consistency of the asymptotic variance *** censoring can be viewed as a way of trimming,it strengthens the robustness of the rank-based high-dimensional inference,particularly for the heavy-tailed model error or the outlier in the presence of the *** evaluate the finite-sample performance of the proposed method via extensive simulation studies and demonstrate its utility by applying it to a subcohort study from The Cancer Genome Atlas(TCGA).

关键词： censoring mechanism heavy-tailed distribution non-smooth loss function outlier rank regression

From"Online Trial"to"Network Govemance":A Perspective on the Functional Transformation of Internet Courts

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Frontiers of law in China-Selected Publications from Chinese Universities 2024年第1期19卷 42-58页

作者： LIU Zhewei ZHANG Chi law school Peking UniversityBeijing 100871China

Internet courts in the 1.0 era achieved initial success in"online trial"and facilitation of the people's access to judicial services,yet lacked the particularity that special courts should have in terms of organization,cases and procedures,making them difficult to fulfill the function of governance of network *** with rule and management,governance has the features of decentralization,broad scope,and co-construction of *** of network society are in line with the structure of social governance *** fulfill their function of governance of network society,internet courts in the 2.0 era,as the integrator of multiple centers and cyberspace as well as the analyzer of internet rules,need to improve in terms of organization,cases and procedures:In terms of organization,consider upgrading internet courts to be intermediate courts and identifying them as cross-region courts in cyberspace;in terms of cases,redefine the essence and extension of"online cases"with elements including wholly cyberspacerelated civil and commercial dispute resolution,new business format management on internet platforms,and governance of data-related rights;and in terms of procedures,improve Internet courts'case selection procedures,judgement effect extension procedures,investigation procedures for independent evidence collection of internet cases,and automatic enforcement procedures ensuring the instant enforcement of judgment,so as to promote a mature and complete legal framework for cyberspace governance.

关键词： internet courts governance centralized jurisdiction internet platforms network governance

International law obligations for the disposal of Fukushima nuclear-contaminated water under the principles of nuclear safety

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Population,Resources and Environment 2024年第1期22卷 10-19页

作者： Wei Gong law school Southwest UniversityChongqing 400715China

The disposal of contaminated water from Japan’s Fukushima nuclear power plant is a significant international nuclear safety issue with considerable cross-border *** matter requires compliance not only with the law of the sea but also with the principles of nuclear safety under international *** principles serve as the overarching tenet of international and China’s domestic nuclear laws,applicable to nuclear facilities and *** principle of safety in nuclear activities is fully recognized in international and domestic laws,carrying broad legal binding ***’s discharge of nuclear-contaminated water into the sea violates its obligations under the principle of safety in nuclear activities,including commitments to optimum protection,as low as reasonably practicable,and *** Japanese government and the International Atomic Energy Agency(IAEA)have breached the obligation of optimum protection by restricting the scope of assessments,substituting core concepts,and shielding dissenting *** the absence of clear radiation standards,they have acted unilaterally without fulfilling the obligation as low as reasonably practicable *** discharge of Fukushima nuclear-contaminated water poses an imminent and unpredictable risk to all countries worldwide,including Japanese *** and the IAEA should fulfill their obligations under international law regarding disposal,adhering to the principles of nuclear safety,including optimum protection,the obligation as low as reasonably practicable,and prevention through multilateral ***,the obligation to provide optimum protection should be implemented by re-evaluating the most reliable disposal technologies and methods currently available and comprehensively assessing various *** standard of the obligation as low as reasonably practicable requires that the minimization of negative impacts on human health,livelihoods,and the environment should not b

关键词： Principles of nuclear safety Disposal of nuclear-contaminated water Optimum protection Prevention As low as reasonably achievable