Most Download articles

    Published in last 1 year | In last 2 years| In last 3 years| All| Most Downloaded in Recent Month| Most Downloaded in Recent Year|

    Most Downloaded in Recent Month
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Research on Lattice Attack on ECDSA Implemented with wNAF
    Journal of Information Security Reserach    2026, 12 (4): 319-.  
    Abstract (106)      PDF (1223KB)(270)       Save
    To mount an attack on the elliptic curve digital signature algorithm (ECDSA) using the windowed nonadjacent form (wNAF) for scalar multiplication, one first requires sidechannel analysis to gather information, followed by latticebased methods to recover the private key. Since the information collected from sidechannel analysis about secret parameters such as the signing private key is partial, it typically necessitates scores or even hundreds of signatures to fully recover the private key. However, in practical attacks, there are stringent limitations on the number of signatures available, making it challenging for attackers to obtain such a large volume of signature data. To maximize the utilization of information gathered through sidechannel analysis and recover the complete private key using only a few signatures, a lattice attack construction method based on the extended hidden number problem (EHNP) is proposed. Initially, cache sidechannel attacks are employed to collect DoubleAddInvert chains during the actual execution of the ECDSA algorithm. Subsequently, these DoubleAddInvert chains are converted into EHNP instances. Next, EHNP is leveraged to construct a lattice matrix, within which exists a target lattice vector bearing the private key. Finally, the block KorkinZolotarev (BKZ) lattice basis reduction algorithm is applied to locate this target lattice vector, thereby recovering the private key. Experimental results demonstrate that the proposed attack scheme can recover the complete signing private key using only two signatures, achieving the theoretical limit.
    Reference | Related Articles | Metrics
    Research on ECDSA Key Recovery Attacks Based on the Extended  Hidden Number Problem
    Journal of Information Security Reserach    2026, 12 (2): 174-.  
    Abstract (149)      PDF (797KB)(265)       Save
    Elliptic curve digital signature algorithm (ECDSA) is one of the most widely used digital signature algorithms. During the signing process, it requires computing scalar multiplication on elliptic curves, which is typically the most timeconsuming component of the signature. In many present cryptographic libraries, the windowed nonadjacent form representation is commonly used to represent the ephemeral key in order to reduce time consumption. This exposes sidechannel vulnerability to malicious attackers, allowing them to extract partial information about the ephemeral key from sidechannel traces and subsequently recover the signing key. Leveraging the extended hidden number problem to extract information from sidechannel traces and applying latticebased attacks to recover keys constitutes one of the mainstream attack frameworks against ECDSA. Based on above, we propose three optimization methods. First, we introduce a neighboring dynamic constraint merge strategy. By dynamically adjusting the merging parameters, we reduce the dimension of the lattice and control the amount of known information lost during the attack, ensuring high success rates for key recovery across all signatures. Second, we analyze and optimize the embedding number in the lattice, reducing the Euclidean norm of the target vector by approximately 8%, thereby improving the success rate and reducing time consumption. Finally, we propose a linear predicate method which significantly reduces the time overhead of the lattice sieving. In this work, we achieve a success rate of 0.99 in recovering the private key using only two signatures.
    Reference | Related Articles | Metrics
    Research on the Path Construction for Effect Evaluation of Artificial Intelligence Integrated Development
    Hu Lina, Lü Xin
    Journal of Information Security Reserach    2026, 12 (10): 879-884.   DOI: 10.12379/j.issn.2096-1057.2026.10.01
    Abstract (128)      PDF (579KB)(107)       Save
    The new-round scientific and technological revolution and industrial transformation are reshaping the global landscape at an unprecedented pace. As a strategic technology driving this transformation, artificial intelligence has become a core focus of global technological competition. Against the backdrop of advancing the “AI+” initiative and fostering new-quality productive forces, artificial intelligence in China has pervaded science and technology, industry, people’s livelihood, governance and other fields. While unlocking socio-economic momentum, it has also given rise to multiple security-related challenges including supply-chain risks, algorithmic ethics, employment polarization. Balancing development and security has gradually become the central thread of artificial intelligence governance. At present, domestic practices of AI integration tend to prioritize industrial scale expansion with insufficient consideration of potential risk costs. Some applications remain at the shallow implementation stage, and in-depth integration needs further improvement. Evaluation tools that take both development benefits and security risks into account are still inadequate. This paper sorts out the multi-dimensional impacts of AI-integrated development on economy, industry, employment and global competition, and analyzes the practical bottlenecks in evaluating its effectiveness. Drawing on differentiated evaluation approaches from the United States, the European Union, Japan and South Korea, it puts forward suggestions on evaluation pathways, so as to provide references for judging the effectiveness of AI-integrated development and coordinating innovative development with whole?chain risk prevention and control.
    Reference | Related Articles | Metrics
    Study of Malware Detection based on Distribution of Assembly Instruction
    Journal of Information Security Research    2015, 1 (3): 267-271.  
    Abstract (370)            Save
    Nowadays, there are more and more various malicious code which cause a huge threat to the computer. In this paper, a variety of assembly instructions are well classified into three categories. And a novel algorithm is presented. In consideration of the relationship between instructions, this paper turn this relationship into probability distributions as the signature of the program. Then, using a large amount of samples to train. The experiment shows that the method proposed in this paper has a significant effect and high accuracy on detecting unknown and metamorphic programs.
    Reference | Related Articles | Metrics
    Overview on SM4 Algorithm
    Journal of Information Security Research    2016, 2 (11): 995-1007.  
    Abstract (1957)      PDF (8653KB)(1246)       Save
    SM4 Algorithm, short for SM4 Block Cipher Algorithm, was published in 2006 to promote the application of WAPI. It became a cryptography industrial standard (GMT 0002—2012) in March 2012 and a national standard (GBT 32907—2016) in August 2016. This paper describes SM4s calculating process, structural features and cryptographic properties. Furthermore, we introduce some latest researches on SM4s security and compare SM4s security with several international block cipher standards such as AES, HIGHT and MISTY1.
    Reference | Related Articles | Metrics
    A Framework for Agent Security Governance
    Gu Hongxun
    Journal of Information Security Reserach    2026, 12 (11): 978-983.   DOI: 10.12379/j.issn.2096-1057.2026.11.01
    Abstract (69)      PDF (574KB)(54)       Save
    Agents are moving from proof of concept to large-scale deployment. However, their autonomous execution can easily lead to behavioral runaway, algorithmic black boxes make decision processes difficult to trace, and cross-domain collaboration blurs accountability boundaries. Accordingly, this paper constructs a “five objectives–four phases–nine measures” security governance framework, which takes trusted identity, controllable authorization, auditable process, traceable accountability and manageable scenario as the objectives, risk observation, runtime management, behavior intervention and capability improvement as the closed-loop phases, and nine capabilities including interaction detection and context protection as the measures. An L1~L5 graded behavior intervention mechanism is further proposed, providing a reusable governance paradigm for full lifecycle security management of enterprise agents.
    Reference | Related Articles | Metrics
    Journal of Information Security Reserach    2022, 8 (8): 812-.  
    Abstract (759)      PDF (4751KB)(348)       Save
    Because deep learning can freely extract and combine features, an increasing number of academics are using it to perform sidechannel attacks without taking into consideration preprocessing processes like choosing sites of interest and alignment. The sidechannel attack model based on deep learning is built with multilayer perceptron networks, convolution neural networks, and recurrent neural networks, but it has several issues in the training stage, such as overfitting, gradient disappearance, and sluggish convergence speed. Meanwhile, the selfattention mechanism is capable of extracting characteristics in natural language processing, computer vision, and other domains. To make the selfattentiveness mechanism accessible to the area of deep learning sidechannel attacks, we present SADLSCA, a deep learning sidechannel attack model based on the selfattentiveness mechanism, based on the features of deep learningbased sidechannel attacks. SADLSCA addresses the issues of fast overfitting, gradient disappearance, and slow convergence of deep learningbased sidechannel attack models during training, and experimentally verifies that the energy traces required for a successful attack on public datasets ASCAD and CHES CTF 2018 are reduced by 23.1% and 41.7%, respectively.
    Related Articles | Metrics
    A Review of Large Language Model-Driven Network Penetration Testing Agents
    Journal of Information Security Reserach    2026, 12 (8): 691-711.   DOI: 10.12379/j.issn.2096-1057.2026.08.02
    Abstract (343)      PDF (3915KB)(102)       Save
    With the accelerated development of artificial intelligence, intelligent agents have demonstrated notable advantages in environmental perception, task planning, and multi-tool coordination. Concurrently, breakthroughs in Large Language Models concerning natural language understanding, logical reasoning, and multimodal processing have provided crucial support for the evolution of intelligent agents. The deep integration of these two technological strands has given rise to LLM-driven autonomous agents for network penetration testing, promoting a gradual shift from the traditional "tool-assisted" paradigm toward "autonomous intelligence." This paper systematically reviews the key challenges and principal technical approaches identified in existing research across four core modules: agent role definition, task planning, memory management, and interactive execution. It further examines the limitations of current methods in areas such as multimodal information processing, automated interaction, and context management. To address these issues, and in view of the ongoing technological evolution of intelligent agents, this paper proposes several promising research directions for intelligent penetration testing. These include multimodal fusion mechanisms, collaborative strategies integrating memory enhancement with reinforcement learning, and knowledge-graph-based vulnerability discovery methods. The analysis indicates that LLM-driven agents for network penetration testing provide substantial technical support for advancing the intelligence and autonomy of cybersecurity operations.
    Reference | Related Articles | Metrics
    A Comprehensive Review of Deepfake Audio Detection Methodologies and Their Applications
    Journal of Information Security Reserach    2026, 12 (9): 813-822.   DOI: 10.12379/j.issn.2096-1057.2026.09.04
    Abstract (214)      PDF (1335KB)(81)       Save
    With the rapid advancement of generative AI technologies, speech synthesized through text to speech and voice conversion has become increasingly realistic,posing a serious threat to public safety. This paper systematically reviews deepfake audio detection methods and their applications across various domains which aids in clarifying the technical developments and application landscape within the field of deepfake audio detection, thereby providing theoretical support and practical references for public safety governance. This study conducted a comprehensive literature review based on an analysis of 70 selected publications from the China National Knowledge Infrastructure (CNKI) and Web of Science databases, covering the period from 2017 to 2025. The research systematically examined progress in deepfake audio technology, experimental datasets, evaluation metrics, and detection methodologies. Furthermore, it synthesized the application status of these detection methods across various domains, including online public opinion monitoring, user privacy protection, multimodal misinformation governance, and voice fraud detection. Findings indicate that current deepfake audio detection primarily relies on end-to-end architectures, which demonstrate superior performance yet limited interpretability, and have been successfully deployed in multiple task scenarios within public security governance. Nevertheless, challenges remain, such as insufficient diversity in deepfake audio datasets, limited generalizability and interpretability of detection techniques, and the need for broader application scenarios. Future research should prioritize the development of more diverse datasets, enhance the generalizability of detection methods, and expand into more varied application domains.
    Reference | Related Articles | Metrics
    A Multimodal Feature Fusion Approach for Vulnerability Detection Based on Large Models
    Zhao Xinjian, Tao Chiyu, Chen Shi, Kuang Boyu, Wu Zicheng, Fu Anmin
    Journal of Information Security Reserach    2026, 12 (11): 984-992.   DOI: 10.12379/j.issn.2096-1057.2026.11.02
    Abstract (52)      PDF (949KB)(44)       Save
    With the widespread adoption of open-source software, the number of vulnerabilities has increased sharply. The traditional detection methods suffer from high false positive rates and difficulty in capturing complex dependencies. To address these issues, this paper proposes a large model-based multi-modal feature fusion vulnerability detection method named MMFVD. The method first constructs a Multi-functional Code Property Graph (M-CPG), which retains key structural information through program slicing and pruning. Next, pre-trained sequence models and graph models are used to extract semantic features and structural features of the code respectively, with online knowledge distillation applied to optimize feature representation. Finally, a dynamic attention mechanism is adopted to achieve adaptive fusion of the features, and a classifier is employed to complete vulnerability prediction. On four public datasets, MMFVD is compared with 10 baseline methods, which verifies the significant advantages of MMFVD in detection accuracy, robustness, and generalization.
    Reference | Related Articles | Metrics
    Journal of Information Security Reserach    2022, 8 (6): 595-.  
    Abstract (215)      PDF (2382KB)(170)       Save
    With the deep integration of industrialization and informatization, the industrial Internet security incidents occur frequently. More and more attackers focus on the critical national infrastructure. In recent years, the scale and complexity of embedded software have increased sharply, especially in the fields of national defense, rail transit, automobile, civil aviation, and industrial control. Users have more strict requirements on the quality of embedded software and require embedded software to be more secure. Based on the collection and analysis of embedded software security coding standards, this article arranges the first allaround list of security vulnerability patterns for embedded software development in China. This list includes the unique security vulnerability patterns of embedded systems, the vulnerability patterns that will cause serious consequences, such as the crash of embedded systems or denial of service, and other vulnerability patterns. Finally, this article briefly introduces the static analysis technology of how to ensure the security of embedded software by using these security vulnerability patterns. Thus, security problems are found at the beginning of the software development process and will be solved in time, so as to better ensure the security of industrial software.
    Related Articles | Metrics
    Apache Shiro Deserialization Attack Detection Model Based on  Attack Characteristics
    Journal of Information Security Reserach    2022, 8 (7): 656-.  
    Abstract (423)      PDF (3615KB)(294)       Save
    As a widely used security framework, Apache Shiro framework provides functions such as authentication, authorization, password and session management, but its deserialization vulnerability is easy to lead to arbitrary code execution, and the existing detection methods have many problems of false positives. Therefore, this paper proposes a detection model of Apache Shiro deserialization vulnerability attack based on attack characteristics. By analyzing the network packet characteristics of normal conditions and vulnerability exploitation, this paper summarizes four attack characteristics, and constructs a model based on this to detect Apache Shiro deserialization vulnerability attack. At the same time, the problem, whether the attack is suspected to be successful is judged and transferred to manual confirmation and disposal. Experimental results show that this method can not only detect Apache Shiro deserialization vulnerability attack, but also further determine whether the attack is suspected to be successful and improve the efficiency of security event handling. In addition, compared with the existing methods, this method can effectively reduce the false negatives rate, so as to reduce the false disposal rate and reduce the impact on normal business.Key words attack characteristic; deserialization; vulnerability detection; Apache Shiro; security event handling
    Related Articles | Metrics
    Secboot’s AI Technology Pushes Identif cation Security to the Cusp of a New Era
    Journal of Information Security Research    2018, 4 (7): 582-587.  
    Abstract (296)      PDF (1248KB)(675)       Save
    Related Articles | Metrics
    Response and Disposal Mechanism for Emerging Intellectual Property Risks Caused by Misuse of Large Model Technologies
    Luo Entao, Wang Juncheng, Bao Hongguang, Peng Tao, Liu Qin, Wu Chuyu
    Journal of Information Security Reserach    2026, 12 (10): 930-937.   DOI: 10.12379/j.issn.2096-1057.2026.10.08
    Abstract (50)      PDF (668KB)(45)       Save
    The in-depth application of generative artificial intelligence has endowed intellectual property (IP) risks associated with large models with new notable characteristics, namely sudden onset, high transmissibility and severe destructiveness, which have posed substantial challenges to conventional governance frameworks. This study focuses on the IP emergencies triggered by the misuse of large model technologies, and aims to construct a response and disposal mechanism integrating intelligent early warning, rapid handling and collaborative coordination. First, this study establishes a multidimensional monitoring indicator system, multi-source data perception framework and dynamic grading rules to achieve precise risk identification and tiered classification. Subsequently, this study designs a standardized disposal workflow centered on immediate containment, evidence preservation and blockchain-based forensic storage, which ensures rapid interruption of risk propagation and provides solid support for subsequent legal accountability. Finally, this study develops a multi-stakeholder collaborative linkage mechanism covering government-enterprise cooperation, cross-sectoral coordination and cross-border interaction, so as to integrate resources, resolve jurisdictional conflicts and generate synergistic effects in risk prevention and control. The proposed mechanism aims to realize a paradigm shift from passive remediation to proactive prevention, and provides a theoretical framework and practical pathways for building an agile and efficient governance system for IP risks in the context of large models.
    Reference | Related Articles | Metrics
    Building Cyber Security Defense by Trusted Computing 3.0
    Journal of Information Security Research    2017, 3 (4): 290-298.  
    Abstract (464)      PDF (1075KB)(2104)       Save
    Related Articles | Metrics
    Journal of Information Security Reserach    2025, 11 (E2): 31-.  
    Abstract (62)      PDF (640KB)(54)       Save
    Reference | Related Articles | Metrics
    Research on Webshell Detection Method Based on Logistic Regression Algorithm
    Journal of Information Security Research    2019, 5 (4): 298-302.  
    Abstract (306)      PDF (1096KB)(762)       Save
    Webshell is a commonly used tool for hackers to carry out network intrusion. It has the characteristics of high concealment and great power. The existing Webshell detection method has high detection accuracy when detecting known Webshell, but the detection accuracy is very low in the face of complex and flexible unknown and variant Webshell. In response to this problem, this paper discusses the characteristics and working principle of Webshell, analyzes the difference between Webshell and the traditional Webshell using obfuscated encryption coding technology, and proposes a Webshell machine learning detection model based on logistic regression algorithm. The model can effectively detect the confusingly coded Webshell, reduce the false positive rate and improve the detection accuracy.
    Reference | Related Articles | Metrics
    Identification, Disposal and Defense of Extortion Virus
    Journal of Information Security Research    2019, 5 (4): 346-351.  
    Abstract (219)      PDF (3416KB)(644)       Save
    Extortion virus mainly spreads in the form of mail, program Trojan horse, web page hanging horse, etc. It encrypts files by using various asymmetric encryption algorithms, and the infected person can not decrypt them generally. Only by getting the decrypted private key, can it be possible to decrypt them. Extortion virus is extremely harsh and extremely harmful. Once infected, it will bring immeasurable loss to users. Therefore, the identification, disposal and defense of extortion virus is particularly important. In the recognition of extortion virus, we usually use the combination of conventional anti-virus software and behavioral identification methods; in the disposal of extortion virus, we can thoroughly clean it up by manual and automatic methods; in terms of defensive measures, traffic level analysis, early warning and terminal level protection and encryption are important links.
    Reference | Related Articles | Metrics
    Survey of Coverage-guided Grey-box Fuzzing
    Journal of Information Security Reserach    2022, 8 (7): 643-.  
    Abstract (697)      PDF (1745KB)(442)       Save
    In recent years, coverageguided greybox fuzzing has become one of the most popular techniques for vulnerability mining, which plays an increasingly important role in the software security industry. With the increasing variety of application scenarios and complexity of test applications, the performance requirements of coverageguided greybox fuzzing are further improved. This paper studies the existing coverageguided greybox fuzzing methods, summarizes its general framework, and analyzes its challenges and the development status. The experimental results of these methods are summarized and the problems existing in the experimental evaluation are discussed. Finally, the future development trend of coverageguided greybox fuzzing is prospected.Key words fuzzing; hole mining; coverageguided; greybox; software security

    Related Articles | Metrics
    Design and Implementation of a Fraud Detection System for Forged Audio and Video
    Wang Xiaoqing, Mao Yiwen, Zheng Zixuan, Wu Yujie, Du Gang
    Journal of Information Security Reserach    2026, 12 (10): 972-977.   DOI: 10.12379/j.issn.2096-1057.2026.10.13
    Abstract (83)      PDF (975KB)(44)       Save
    In recent years, with the rapid iterative development of information technology, tactics of telecom and cyber fraud have continued to evolve and upgrade. Fraudsters increasingly utilize generative artificial intelligence (AI) technologies such as deepfakes to fabricate or tamper with specific identity information with high fidelity, and carry out targeted telecom and cyber fraud on this basis. This issue has gradually become a prominent challenge in the prevention and governance of telecom and cyber fraud. To address these risks and problems, this research innovatively constructs a comprehensive multimodal deepfake detection system, which can identify AI-generated images, AI voice replacement, and AI face swapping. Meanwhile, an end-side lightweight multimodal detection SDK is also developed. The proposed system can be widely applied to a variety of business scenarios, including multimedia messages covering text, images, audio, video and virtual scenarios, 5G new calls, video conferences, and trusted identity authentication. It aims to provide flexible, efficient and accurate AI authenticity verification, early warning and authentication framework and capability for all industries.
    Reference | Related Articles | Metrics
    Research on Log Anomaly Detection Method Integrating Semantic Features
    Journal of Information Security Reserach    2026, 12 (4): 383-.  
    Abstract (127)      PDF (5672KB)(92)       Save
    With the continuous expansion of system functionalities, the volume of system logs has grown exponentially, presenting substantial challenges to conventional anomaly detection approaches. Deep learningbased log anomaly detection techniques have gradually become a research hotspot due to their powerful feature extraction capabilities. This study proposes a semisupervised log anomaly detection model LogSem, which integrates semantic features. By introducing log content vectors that contain semantic information of the main log content and incorporating masked log key prediction tasks and hypersphere volume minimization tasks for semisupervised learning, the model deeply explores the semantic features of logs. Experiments conducted on three mainstream datasets show that the proposed method outperforms the LogBERT baseline model in terms of the F1 score. Furthermore, this study explores and verifies the feasibility of addressing the outofvocabulary problem through semisupervised learning.
    Reference | Related Articles | Metrics
    A Dual-Modal Dynamic Feature Fusion Detection Method for Smart Contract Vulnerabilities Oriented to Lightweight Deployment
    Yang Fangping, Nie Lixia, Li Binghui
    Journal of Information Security Reserach    2026, 12 (10): 958-963.   DOI: 10.12379/j.issn.2096-1057.2026.10.11
    Abstract (81)      PDF (578KB)(47)       Save
    Most vulnerability detection methods for smart contracts rely on a single modality or large models. The former suffers from insufficient extraction of key features, resulting in low detection accuracy, while the latter has a large parameter scale, which is not conducive to deployment in resourceconstrained environments. To address these issues, this paper proposes dualmodal conditional feature gating, a lightweight dynamic feature fusion method for smart contract vulnerability detection, which adaptively generates fusion weights via a lightweight gating network and constructs a lightweight deploymentoriented detection framework. Experiments on 17,554 reentrancy samples from SmartBugs Wild achieve an accuracy of 76.87%, an F1score of 0.788, and an AUC of 0.870, outperforming static fusion, concatenation fusion, and singlemodal baselines. Compared with reproduced MVul-L and CMRL, the proposed method maintains comparable performance while reducing the parameter count by about 45% and lowering inference latency.
    Reference | Related Articles | Metrics
    Quantitative Research on Privacy Risk of LargeScale Mobile Users
    Journal of Information Security Research    2019, 5 (9): 778-788.  
    Abstract (790)      PDF (3810KB)(628)       Save
    The increasing number of mobile applications have given mobile Internet service providers the opportunity to collect large amounts of user data. However, the unreasonable and abnormal collection and use of data have made mobile users face extremely serious privacy risk. How to analyze the status of user privacy risk and protect user privacy have become an urgent issue. Based on the permission analysis of mobile applications, this paper proposes a novel user privacy risk quantification model. This model first identifies the personal privacyrelated data collection of mobile applications through 39 privacy permissions which are considered as leakage data source, then consider the possibility of data leakage and the privacy hazard degree of data. This model is further constructed with the assist of application usage data of 30 million mobile devices. Finally, the distribution of privacy risks of individual users is analyzed. Then through analyzing the average user privacy risk value of each user group, the China privacy risk index is formulated to reflect the differences in privacy risks among various user groups, including the regional privacy risk index, the population privacy risk index, and the behavioral privacy risk index.
    Reference | Related Articles | Metrics
    Progress Challenges and International Cooperation in Artificial Intelligence Safety Standardization
    Hu Chengchun, Bi Yu
    Journal of Information Security Reserach    2026, 12 (10): 885-891.   DOI: 10.12379/j.issn.2096-1057.2026.10.02
    Abstract (102)      PDF (602KB)(49)       Save
    The rapid development of Artificial Intelligence (AI) technologies and the expansion of their applications place greater demands on the development and effective implementation of AI safety and security standards. This paper reviews the AI safety and security standardization initiatives of international organizations, including ISO/IEC, ITU, and IEEE, compares standardization practices in the United States, the European Union, and China, and analyzes the major challenges facing China in this field. It argues that AI safety and security standards are evolving from individual technical specifications toward lifecycle-wide governance. However, China continues to face several challenges: standards development lags behind rapid technological advances; general safety and security requirements are difficult to reconcile fully with sector-specific needs; and international differences in governance approaches complicate standards alignment. To address these challenges, this paper recommends strengthening research on key technologies and coordination between research and development, testing, and evaluation; improving domestic coordination and alignment between general standards and sector-specific specifications; and advancing alignment with international rules and joint validation. These measures aim to enhance the verifiability, adaptability, and effectiveness of China’s AI safety and security standards and strengthen its capacity to participate in international standardization.
    Reference | Related Articles | Metrics
    Chinese Dark Web Product Detection and Classification Based on  Multimodal Data Augmentation#br#
    Journal of Information Security Reserach    2026, 12 (6): 575-.  
    Abstract (114)      PDF (4502KB)(71)       Save
    In order to address the issues of coarse granularity in existing dark Web intelligence classification research and the predominance of Englishlanguage datasets, this paper proposes a finegrained analysis study focused on Chinese dark Web content. To overcome the scarcity of Chinese dark Web data and the misalignment of multimodal data, this study employs a large language model prompt rewriting strategy and a differentiated image enhancement strategy to achieve text and image data augmentation. By integrating product data from a certain platform on the Surface Web, a dataset comprising 14,052 product records was constructed. A feature selection optimization module was designed to establish an intertask coupling mechanism, and a Chinese dark Web product detection and classification model based on multimodal data augmentation was proposed. Experimental results demonstrate that the proposed model achieves macroF1 scores of 0.992 and 0.941 in dark Web product detection and classification tasks, respectively, representing an approximately 2% improvement over the best baseline model in  classification task and significantly outperforming existing singlemodal and multimodal methods. This approach effectively enhances the performance of finegrained classification tasks for Chinese dark Web intelligence, offering new insights and methodologies for dark Web intelligence analysis.
    Reference | Related Articles | Metrics
    A Construction Method of Hybrid Covert Channels Based on Federated Learning
    Journal of Information Security Reserach    2026, 12 (9): 789-800.   DOI: 10.12379/j.issn.2096-1057.2026.09.02
    Abstract (147)      PDF (3249KB)(88)       Save
    Federated Learning (FL) is designed to solve the irreconcilable contradiction between data sharing requirements and privacy needs. As a kind of distributed machine learning, FL needs to exchange a large number of model parameters between participants and the central server, which leads to a large amount of data communication. The iterative process of FL model updating depends on distributed data transmission, and once the transmission channel is located, its model data security and integrity will be difficult to guarantee. In this paper, a hybrid Covert Storage-Timing Channel (CSTC) scheme for FL is proposed. The secret message is firstly split into parallel-distributed coding units, and the secret data communication is achieved via adjusting the inter-packet delays to indicate which block is to be transmitted, and the overt traffic’s packet payload is selectively replaced with secret blocks according to the payload content. Thus, the position indicator of a secret block is embedded in both the time and storage features of the overt traffic, while the feature-location correspondence is pre-shared by the receiver and sender, and the adversary cannot grasp a secret message unless all features locating the secret block are obtained. Moreover, three variants of the original CSTC are proposed to fulfill the different performance requirements, and the experiments show that the undetectability and capacity of the proposed schemes are reasonable.
    Reference | Related Articles | Metrics
    SAFE-SCVDM: Sequence Feature-Enhanced Smart Contract Vulnerability Detection Model
    Journal of Information Security Reserach    2026, 12 (9): 842-849.   DOI: 10.12379/j.issn.2096-1057.2026.09.07
    Abstract (103)      PDF (943KB)(52)       Save
    Aiming at the insufficient integration of local features and global features in existing smart contract vulnerability detection methods, as well as inadequate modeling of code contextual dependencies, this paper proposes a sequence feature-enhanced vulnerability detection model for smart contracts-SAFE-SCVDM. The model innovatively integrates multi-dimensional code representations through a three-stage feature extraction architecture to improve detection accuracy. First, we design a structured traversal based transformation strategy for abstract syntax trees , converting AST into sequential structures that preserve lexical and hierarchical features. Second, a node extraction script is developed to mine token-level information from smart contract code, retaining semantic characteristics. Subsequently, global contextual dependencies are captured by leveraging a large-scale code model to generate code comments from source code, thereby preserving cross-function semantic relationships. Finally, an enhanced LoRA detection model is proposed, utilizing a self-attention mechanism to jointly model textual sequences (code tokens), structural sequences (SBT-AST), and global annotations (code comments). Experimental results demonstrate that the proposed method achieves an accuracy of 88.41% in smart contract vulnerability detection, outperforming state-of-the-art baseline models by 9.8%.
    Reference | Related Articles | Metrics
    An IoT Intrusion Detection Method Based on Adaptive Feature Optimization and Boundary-Balanced Sampling
    Chen Liangchen, He Boshu, Jiang Zilong, Jiang Zhengwei, Lu Zhigang, Liu Baoxu
    Journal of Information Security Reserach    2026, 12 (10): 948-957.   DOI: 10.12379/j.issn.2096-1057.2026.10.10
    Abstract (82)      PDF (1067KB)(46)       Save
    To address the performance bottlenecks in IoT intrusion detection caused by resource-constrained devices, high-dimensional redundant traffic features, and imbalanced attack sample distributions, we propose an IoT intrusion detection method that integrates adaptive feature optimization and boundary-balanced sampling. First, to mitigate the increased computational overhead and classification interference caused by high-dimensional redundant features in IoT traffic data, we design an adaptive cross-validation recursive feature selection algorithm based on Light Gradient Boosting Machine (LightGBM), termed LightGBM-based Adaptive Cross-Validation Recursive Feature Selection (LARFS). This algorithm combines feature importance evaluation with a cross-validation recursive feature elimination mechanism and adaptively searches for the optimal feature subset, thereby effectively reducing feature dimensionality while maintaining detection performance. Second, to overcome the class imbalance in IoT traffic and the boundary noise introduced by conventional oversampling methods, we propose a data balancing method termed Weighted Borderline-SMOTE and Tomek-ENN-based Data Balancing (WBSTE), which combines weighted Borderline-Synthetic Minority Over-sampling Technique (weighted Borderline-SMOTE) with Tomek links and Edited Nearest Neighbors (ENN). By enhancing boundary samples, removing class overlap, and cleansing noise, WBSTE effectively improves the model’s ability to recognize minority attack samples. Experimental results on the N-BaIoT dataset demonstrate that the proposed method achieves high detection accuracy and low computational overhead, making it well-suited for resource-constrained IoT environments.
    Reference | Related Articles | Metrics
    “Internet +”Power: Overview of Westone Secruity’s Cyber Secruity
    Journal of Information Security Research    2016, 2 (10): 862-875.  
    Abstract (416)      PDF (2788KB)(1199)       Save
    Related Articles | Metrics
    Computing Force Network Security Architecture and Data Security Governance Technology
    Journal of Information Security Reserach    2022, 8 (4): 340-.  
    Abstract (1053)      PDF (2657KB)(666)       Save
    As a new information infrastructure which provides deep integration of computing force and network services, computing force network (CFN) provides important support for national cyber power, digital China and smart society. At present, the planning and construction of CFN has entered a critical period, and the work related to CFN security is gradually advancing, but the systematic security architecture has not been formed. This paper summarizes the relevant research progress of CFN, analyzes the security opportunities and challenges faced by CFN, and proposes a security reference architecture based on sorting out the key security technologies, so as to provide a reference for promoting the construction of CFN security system and deploying CFN security mechanism.Key words computing force network; new information infrastructure; security reference architecture; orchestration security; privacy computation; data security; artificial intelligence
    Related Articles | Metrics
    PeopleNet, Independently Developing Core Technology of Cyber Information Security
    Journal of Information Security Research    2017, 3 (7): 578-588.  
    Abstract (467)      PDF (1448KB)(914)       Save
    Related Articles | Metrics
    The Reasearch of Internet Identity System Based on eID and Personal Information Protection Legal System
    Journal of Information Security Research    2019, 5 (5): 440-447.  
    Abstract (341)      PDF (1072KB)(736)       Save
    The identity of users in cyberspace is virtual and difficult to determine, which makes it difficult to effectively manage the disordered state of cyberspace virtual society. The Internet real-name system is an Internet management method based on the real name of the user. It is an important means and system for restraining, guiding and protecting Internet users. However, with the arrival of big data era, more and more information exist in the cyberspace, and personal information leakage incidents are common. The Internet identity management system based on the Internet electronic identity (eID) can ensure that the Internet service agencies can effectively identify users' real identity without disclosing their personal information, which provides a good solution to the conflict between the Internet real-name system and personal information protection. At present, China's Internet electronic identity management is still in the preliminary development and pilot application stage, and relevant legal system is still not perfect, which must be explored.
    Reference | Related Articles | Metrics
    A Survey of SQL Injection Attack Detection and Defense Technology
    Journal of Information Security Reserach    2023, 9 (5): 412-.  
    Abstract (980)      PDF (2612KB)(480)       Save
    In the era of “Internet+”, data is the most valuable resource of the Internet. Attackers often use SQL injection attacks to destroy the database in order to obtain important data information in the database. The threat to database security is becoming more and more serious. At present, the research on SQL injection attacks mostly focuses on traditional SQL injection attacks, but lacks the cognition of new advanced SQL injection technology with stronger concealment and higher risk, and the research on related detection and defense technology. In response to this phenomenon, this paper analyzes and evaluates traditional and advanced SQL injection attack technologies and their technical characteristics based on the classification of SQL injection technologies; summarizes existing detection and defense technologies, and evaluates the advantages and disadvantages of these methods for defense effectiveness; finally The problems existing in the current research field are sorted out, and suggestions for future research directions are put forward.

    Reference | Related Articles | Metrics
    Research on the Security Mechanism of Large Language Model
    Sun Qi, Li Yang
    Journal of Information Security Reserach    2026, 12 (10): 892-898.   DOI: 10.12379/j.issn.2096-1057.2026.10.03
    Abstract (102)      PDF (875KB)(52)       Save
    Large model security is a core issue in Artificial Intelligence(AI) governance, and its complexity far exceeds that of traditional cybersecurity and software vulnerability management. From the perspective of complex adaptive systems, this paper deconstructed large model security into a dynamic system shaped by the interaction of attack, defense, and vulnerability, examined its connotations, extensions, and constituent elements, and identified three major trends in its evolution. It argued that attack was essentially adaptive perturbation, defense was essentially resilience enhancing, and vulnerability was a tension node in the system structure that embodied both destructive potential and improvement value. The security boundary of large models is expanding from discrete points and chains toward the full life cycle, with technology, institutions, and openness jointly sustaining its effective operation. Accordingly, this paper put forward recommendations across three dimensions, namely technological offense and defense, governance rules, and international cooperation, so as to promote the construction of a security theory system commensurate with AI development and better implement the strategic requirement of coordinating development and security.
    Reference | Related Articles | Metrics
    Research on Cyber-Attack Defense System Based on Big Data and Threat Intelligence
    Journal of Information Security Research    2019, 5 (5): 383-387.  
    Abstract (476)      PDF (1670KB)(1449)       Save
    Cyber-attacks are the use of network vulnerabilities and security flaws to attack the hardware, software and data of a cyber system. The earlier a cyber-attack is identified, the less adverse effect it has. The traditional network intrusion detection system (IDS) has some limitations in detecting cyber-attacks, such as passive protection and limited capability of threat identification. Threat intelligence technology provides a more scientific and effective method for identifying potential or actual cyber-attacks by using big data analysis,and provides a comprehensive and relevant cyber-attack defense model.
    Reference | Related Articles | Metrics
    Research on Maintenance and Security of Industrial Control Networks in Electric Power Industry
    Journal of Information Security Research    2019, 5 (8): 679-684.  
    Abstract (303)      PDF (2038KB)(817)       Save
    As an important part of national key infrastructure, the importance of operation and maintenance security of electric power industry control network is selfevident. Especially with the increasing security incidents of industrial control networks in the world in recent years, effective measures must be taken to protect the safe operation of industrial control networks, which also puts forward higher requirements for the operation, maintenance and safety protection of industrial control networks and industrial systems. Through indepth analysis of the characteristics of industrial control network in electric power industry, especially the key characteristics of the data type and network topology structure of the electric power network, effective operation and maintenance methods and security risk prevention methods are put forward. In operation and maintenance, the backup of system data and the state monitoring of the system itself are strengthened. Security measures, such as physical isolation, industrial control flow monitoring, fault recovery management and so on should be taken, and effective policies and behavioral norms should be provided. Finally, form safety protection measures suitable for electric power industry control network, to achieve the purpose of safe operation of the electric power industry control network.
    Reference | Related Articles | Metrics
    Keytarget Face Recognition Scheme Based on Homomorphic  Encryption and Edge Computing
    Journal of Information Security Reserach    2024, 10 (11): 1004-.  
    Abstract (403)      PDF (2205KB)(141)       Save
    With the promotion of China’s comprehensive national strength and international status, more and more major international events are held in China’s firsttier cities, such as the 31st Chengdu Universiade and the 19th Hangzhou Asian Games. The huge flow of people and complex crowd categories have caused considerable security pressure on the security team. Because the traditional face recognition system realizes face recognition in the central server in plaintext state and relies on the traditional state secret algorithm to ensure security, the computational efficiency and security of the whole system cannot be fully guaranteed. Therefore, based on the CKKS homomorphic encryption scheme and Insightface face recognition algorithm, this paper proposes a keytarget face recognition scheme supporting edge computing. Firstly, the key face features are encrypted by the CKKS homomorphic encryption scheme, and the ciphertext data are distributed to each frontend monitoring device. After that, the frontend monitoring device is responsible for extracting the face features of the scene crowd and calculating the matching degree with the ciphertext database. Finally, the ciphertext calculation results are returned to the central server and decrypted. Experimental results show that the recognition accuracy of the proposed scheme is 98.2116% when the threshold is 1.23 on LFW data sets, which proves the reliability of the proposed scheme.
    Reference | Related Articles | Metrics
    Federated Learning Backdoor Attack Based on Constrained Perturbation and Loss Regulation
    Journal of Information Security Reserach    2026, 12 (3): 210-.  
    Abstract (141)      PDF (3353KB)(97)       Save
    Federated learning, as a distributed machine learning framework, enables multiparty collaborative training with data isolation and privacy protection, However, its decentralized architecture makes it vulnerable to backdoor attacks. This paper proposes a federated learning backdoor attack method based on the constrained perturbation and loss regulation (CPR). The method realizes backdoor implantation and proliferation through three modules: input perturbation, dynamic weight regulation, and secondary perturbation reinforcement. Input perturbation introduces constraintbased noise to poison the training samples. Dynamic weight regulation dynamically adjusts the task weights by introducing cosine annealing, which realizes the balance between backdoor feature learning and main task performance. Secondary perturbation reinforcement utilizes dynamic loss values to further perturb the poisoned samples and reinforce its backdoor features. The CPR backdoor attack is evaluated on MNIST, FashionMNIST and CIFAR10 datasets, and the experimental results show that the CPR backdoor attack is able to significantly improve the success rate of the attack while maintaining the accuracy of the model’s primary task and exhibits higher stealth and persistence under a variety of data distribution conditions, as compared to pixel, labelflipping and hybrid attacks.
    Reference | Related Articles | Metrics
    Research on the Implementation Path of Zero Trust Strategy
    Journal of Information Security Reserach    2026, 12 (5): 483-.  
    Abstract (100)      PDF (3588KB)(86)       Save
    Amid the wave of digital transformation, the traditional boundarybased network security model is increasingly ineffective in dynamic and border less environments. The United States has taken the lead in restructuring its cybersquatting system through a systematic zerotrust strategy, and its trinity practice path of “policytechnologyecology” is of reference significance for China to build a digital security barrier. This paper uses case analysis and policy comparison methods to deeply analyze the toplevel design logic, core technological breakthrough points, and ecological coordination mechanisms of the U.S. zerotrust strategy, revealing its essence of transitioning from “passive protection” to “active immunity”. Based on a deep diagnosis of the complexity of China’s ultralargescale network ecosystem, the shortcomings in the autonomy of core technologies, and the challenges of data sovereignty governance, this paper proposes a Chinesestyle “fourdimensional integrated” implementation path: breaking the fragmented dilemma with systematic toplevel design; breaking through technological bottlenecks with the integration of national cryptography and AIdriven technologies; building a security ecosystem with costsharing and standard leadership through governmententerprise collaboration; and addressing implementation limitations with scenario classification and privacy enhancement. The study emphasizes that China needs to innovate on the basis of reference, take zero trust as an important engine for building a digital security barrier, and balance the needs of security protection with the development of the digital economy.
    Reference | Related Articles | Metrics
    Research of the Index of National Cybersecurity
    Lv Xin
    Journal of Information Security Research    2016, 2 (9): 766-773.  
    Abstract (351)      PDF (1086KB)(918)       Save
    Related Articles | Metrics