Table of Content

15 October 2025, Volume 11 Issue 10

Previous Issue   

Research on Critical Information Infrastructure Security Protection

2025, 11(10):  878. 

Asbtract ( )   PDF (324KB) ( )  

Related Articles | Metrics

Research on Security Assurance of Egovernment

2025, 11(10):  879. 

Asbtract ( )   PDF (865KB) ( )  

References | Related Articles | Metrics

government encompasses critical domains including government operations, public services, and data management, and its security directly affects national interests, public wellbeing, and social stability. In recent years, cyberattacks targeting Egovernment systems have become more frequent and continue to rise, security risks of government administrative networks continued to mount up and challenge security protection. This paper analyzes the development paths of Egovernment security protection at home and abroad and proposes relevant policy recommendations, with the aim of providing strong support for building a more perfect and optimized Egovernment security protection system.

The Enlightenment and Reference of Cybersecurity Protection Policies for  Critical Information Infrastructure

2025, 11(10):  885. 

Asbtract ( )   PDF (920KB) ( )  

References | Related Articles | Metrics

The security and stability of critical information infrastructure (CII) are of crucial importance to national security, economic development, and social stability. The insights and lessons learned from the CII security safeguards policies of countries and organizations such as the European Union, Japan, the United States, and Russia merit reference. CII security safeguards policies in China has gone through the stages of early exploration, rapid development, and comprehensive advancement; it is confronted with real predicaments including insufficient policy foresight, inadequate crossdomain coordination and collaboration, poor coordination and alignment of standards, and weak discourse power in international rules. It is suggested that China should strengthen the strategic guidance and toplevel design for CII, improve the crossdomain overall planning and linkage mechanism, formulate and refine CII protection standards.

Research on Highquality Development of New Infrastructures Under  Critical Information Infrastructure Security Protection

2025, 11(10):  891. 

Asbtract ( )   PDF (957KB) ( )  

References | Related Articles | Metrics

Developing new infrastructure plays a crucial role in enhancing the security protection capabilities of critical information infrastructure. The approaches adopted by relevant countries in advancing new infrastructure—such as boosting global competitiveness, prioritizing key technology R&D, attracting deep private sector participation, promoting unified standards and regulations, and strengthening supply chain resilience—offer valuable insights. Although China’s new infrastructure has seen continuous improvements in recent years regarding development scale, technological autonomy, digital and intelligent capabilities, and its capacity to support critical infrastructure, it also faces challenges such as significant intrinsic security risks, risks associated with introducing new technologies, and lagging standardization efforts. It is recommended in terms of to drive the highquality development of new infrastructure by leveraging intelligent upgrades as the driving force, functional expansion as the connecting link, and boundary governance as the focal point.

A Symbioticbased Framework for AI Safety Governance

2025, 11(10):  897. 

Asbtract ( )   PDF (2070KB) ( )  

References | Related Articles | Metrics

Artificial intelligence technology is currently developing at an unprecedented pace, with safety concerns becoming a global focal point. Traditional AI safety research has predominantly relied on a “control paradigm”, emphasizing limitations, regulations, and value alignment to control AI behavior and prevent potential risks. However, as AI capabilities continue to strengthen, unidirectional control strategies are revealing increasingly significant limitations, with issues such as transparency illusions, adversarial evolution, and innovation suppression gradually emerging. Industry leaders like Sam Altman and Dario Amodei predict that AI may comprehensively surpass human capabilities in multiple fields within the next 23 years, making the reconstruction of AI governance paradigms particularly urgent. This paper proposes a new perspective—the “symbiotic paradigm”—emphasizing humanmachine collaboration as the core and understanding and trust as the foundation. Through establishing four pillars: transparent communication, bidirectional understanding, creative resonance, and dynamic boundaries, it promotes AI safety’s transition from control to cocreation, serving as one of the foundational paths for digital governance transformation. This paper systematically demonstrates the feasibility and necessity of the symbiotic paradigm through four dimensions: theoretical analysis, technological paths, practical cases, and governance recommendations, aiming to provide a sustainable alternative for future AI safety research and digital governance practices.

TCNGANbased Temporal Traffic Anomaly Detection

2025, 11(10):  907. 

Asbtract ( )   PDF (2708KB) ( )  

References | Related Articles | Metrics

In recent years, generative adversarial networks have been widely used in the field of temporal anomaly detection. However, temporal data often has complex timedependence, and problems such as gradient vanishing and training instability are common in existing anomaly detection models. To this end, this paper proposes an unsupervised temporal traffic anomaly detection model based on the combination of temporal convolutional network (TCN) and GAN. The model uses TCN as the infrastructure of generator and discriminator, which can effectively capture the temporal features of the temporal traffic data. During the anomaly detection process, the model constructs an anomaly scoring function based on the reconstruction loss and discriminator loss, and performs anomaly judgment by setting a threshold, thus improving the accuracy of anomaly detection. To verify the performance of the proposed model, experiments are conducted on five different types of datasets. The results show that the average F1 score of the proposed model is 11.02% higher than that of the TAnoGAN model.

Research on Traffic Anomaly Detection Method and System for API Gateway

2025, 11(10):  917. 

Asbtract ( )   PDF (1061KB) ( )  

References | Related Articles | Metrics

With the rise of cloud services and the widespread use of API technology, many network capabilities of operators are usually outputted and empowered through APIs. API gateways have become an important way for northsouth and eastwest system interconnection and data sharing. This paper proposes a method for API gateway traffic anomaly detection based deep learning. Firstly, a heterogeneous graph is constructed to comprehensively represent the gateway traffic network. Then, based on graph attention neural network, node representations in the heterogeneous graph are learned by considering both structural and temporal dimensions. We introduce graph structure refinement to compensate for sparse connections between entities in the heterogeneous graph and obtain more robust node representation learning; Finally, the meta learning algorithm is used to optimize the model and improve its generalization ability in small sample scenarios. The model can be deployed on gateway devices. The algorithm model was experimentally evaluated on the CICIDS2017 dataset, and the results showed that compared with the baseline algorithm, the detection method proposed in this paper has good performance in small sample and multi classification problems.

Robust Malicious Encrypted Traffic Detection Method Based on  Dual Confidence Sample Selection

2025, 11(10):  924. 

Asbtract ( )   PDF (1679KB) ( )  

References | Related Articles | Metrics

In the task of detecting malicious encrypted traffic, the existence of noise tags seriously affects the generalization ability and detection accuracy of the model. To solve the above problems, a noise label learning method based on DCASS (dualconfidence adaptive sample selection) is proposed to realize robust malicious encryption traffic detection. Firstly, the low dimensional features of samples are extracted by self encoder, and the feature confidence of samples is constructed.Then, the label confidence of samples is evaluated according to their performance in classification training. Finally, an adaptive selection threshold is proposed to select samples based on the dual confidence of feature space and label space, and filter noise samples dynamically to improve the robustness of the model. Experiments on CIRACICDoHBrw2020 dataset show that the proposed method has good performance and stability in dealing with noise labels. The F1 scores of the method reach 86.686%, 86.749%, 83.199% respectively when the noise rate is 20%, 30%, 40%. Compared with the existing three methods, the method proposed in this paper shows the best performance under different noise rates, with the average performance improvement of 18.89%, 37.34%, 6.32% respectively.

Research on Sidechannel Attack Methods of IKE Protocol

2025, 11(10):  933. 

Asbtract ( )   PDF (1880KB) ( )  

References | Related Articles | Metrics

Analyze the implementation of the IKE protocol, construct an IKE protocol message generation model, and verify three sidechannel attack methods against the IKE protocol under security assumptions and DolevYao threat models. Attackers can obtain users’ privacy information, and increase the number of target user tags they possess, based on which targeted attack methods and tools can be selected. For the three potential security risks that may cause privacy breaches, the information entropy algorithm is introduced for quantitative evaluation. By calculating the changes in information entropy, the impact of different privacy information breaches on user security is quantitatively analyzed, which is beneficial for users to take targeted security protection measures. The experimental results verified the effectiveness of three sidechannel attack methods, and also proved that the information entropy quantification evaluation method can clearly characterize the degree of harm caused by privacy leakage, providing a basis for users to formulate security protection measures and helping to reduce potential privacy leakage risks.

Imperceptible Proactive Defense Method Against Face Attribute Editing

2025, 11(10):  941. 

Asbtract ( )   PDF (2504KB) ( )  

Related Articles | Metrics

Although the face attribute editing forgery active defense method based on generative adversarial network (GAN) generates adversarial perturbations faster than the gradient attackbased methods, existing methods still fail in balancing the proactive defense effect with the imperceptibility of generated perturbations. Therefore, this paper proposed a highly imperceptible proactive defense method against face attribute editing based on GAN. To enhance the imperceptibility of the perturbations, the method designed a highfrequency information compensation mechanism to enable the generator to generate more highfrequency perturbations that are less sensitive to the human eye. To improve the proactive defense performance of generated perturbations, the proposed method also designed a multilevel dense connection mechanism for reducing semantic loss during the encoding process. Meanwhile, the method introduced face saliency adversarial loss in training stage to enable perturbations to disrupt face forgery areas better. The experiments were conducted in both singlemodel and crossmodel defense scenarios. The results indicate that compared to existing methods, the proposed method generates more imperceptible adversarial perturbations and obtains high success rates for defending against target models.

DGA Domain Name Generation Method of BiLSTM Model  Based on Bayesian HPO

2025, 11(10):  950. 

Asbtract ( )   PDF (1488KB) ( )  

References | Related Articles | Metrics

In recent years, domain generation algorithms (DGA) have been extensively utilized in network attacks to dynamically generate large quantities of random domain names for malicious software communications, posing a severe challenge for security defenses. As DGA structures grow increasingly complex, traditional domain classification methods that rely on manually extracted features struggle to adapt to new variants in a timely manner. Although generationbased deep models can automatically capture latent patterns from data, their large parameter sizes and intricate hyperparameter tuning often hinder stable performance across diverse DGA. To tackle these issues, this paper proposes a DGA domain generation approach based on a bidirectional long shortterm memory (BiLSTM) model enhanced by Bayesian hyperparameter optimization(Bayesian HPO). By automating the tuning of critical hyperparameter, our method significantly reduces manual intervention and training overhead, while strengthening the robustness and generalization capability of the model against various DGA. Experimental results demonstrate that the proposed approach achieves excellent generation accuracy on multiple DGA families, providing a proactive, forwardlooking defense strategy for network security.

Research on Multimodal Cyberspace Identification Technology  Based on Object Identifier

2025, 11(10):  960. 

Asbtract ( )   PDF (1253KB) ( )  

References | Related Articles | Metrics

Multimodal cyberspace identification is a basic work for the construction of multimodal cyberspace. This paper summarizes the current state of identification system research both domestically and internationally, and provides a comparative analysis of various identification technologies. In view of the large number of communication devices in multimodal cyberspace and the high requirements of endogenous security, a multimodal cyberspace identification technology based on object identifiers is proposed, and the coding rules of tree structure are used to identify and manage largescale communication devices in multimodal cyberspace to improve management efficiency.

Government Data Catalog Security Sharing Model Based on Editable Blockchain

2025, 11(10):  966. 

Asbtract ( )   PDF (6159KB) ( )  

References | Related Articles | Metrics

As government demand for data sharing rises, ensuring data security and reliability has become critical. This paper proposes a secure sharing model for government data catalogs using editable blockchain, which facilitates collaborative updates both onchain and offchain, incorporates finegrained editing permissions, and implements robust security controls. The model employs a dualtrapdoor chameleon hash function with a temporary trapdoor key for onchain updates, addressing the problem that traditional key splitting and recovery schemes cannot balance security and efficiency. Additionally, it introduces an editing permission authorization mechanism that combines user IDbased multiinstitution attribute encryption with temporary trapdoor keys, ensuring accurate permission management across departments. A thorough security analysis confirms the model’s effectiveness in mitigating various security threats. The analysis reveals that the proposed model significantly enhances the trustworthiness of government data sharing by effectively addressing security challenges and ensuring data integrity. These findings highlight the potential of editable blockchain technology in transforming how government entities manage and share sensitive information.