Most Read articles

Published in last 1 year |  In last 2 years |  In last 3 years |  All

In last 3 years

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

ChatGPT’s Applications, Status and Trends in the Field of Cyber Security Journal of Information Security Reserach    2023, 9 (6): 500-.   Abstract （907）      PDF （2555KB）（717）       Knowledge map    Save ChatGPT, as a large language model technology, demonstrates extremely strong language understanding and text generation capabilities. It has not only attracted tremendous attention across various industries but also brought new transformations to the field of cybersecurity. Currently, research on ChatGPT in the cybersecurity field is still in its infancy. To help researchers systematically understand the research status of ChatGPT in cybersecurity, this paper provides the first comprehensive summary of ChatGPT’s applications in the field of cybersecurity and potential accompanying security issues. The article first outlines the development of large language model technologies and briefly introduces the technology and features of ChatGPT. Then, it discusses the enabling effects of ChatGPT in the cybersecurity field from two perspectives: assisting attacks and assisting defense. This includes vulnerability discovery, exploitation and remediation, malicious software detection and identification, phishing email generation and detection, and potential use cases in security operations scenarios. Furthermore, the article delves into the accompanying risks of ChatGPT in the cybersecurity field, including content risks and prompt injection attacks, providing a detailed analysis and discussion of these risks. Finally, the paper looks into the future of ChatGPT in the cybersecurity field from the perspectives of security enablement and accompanying security, pointing out the direction for future research on ChatGPT in the cybersecurity domain. Reference | Related Articles | Metrics

Select

Research on the Application of Commercial Cryptography in 5G Network Journal of Information Security Reserach    2023, 9 (4): 331-.   Abstract （645）      PDF （1197KB）（376）       Knowledge map    Save As a new generation of mobile communication network infrastructure, 5G application scenarios run through all aspects of production and life, such as industrial Internet, energy industry, transportation, medical industry and education. However, unprecedented security risks have been brought to 5G networks, including massive terminal access, largescale network deployment, and massive data aggregation. 5G security has gradually become a worldwide research trend in recent years since it is crucial to social development, economic operation, and even national security. Cryptography is the core technology and basic support to assure network and information security. After more than ten years of development, national commercial cryptographic algorithms ZUC, SM4, SM3, SM2, whose independent intellectual property rights are available, have gradually exerted more indispensable effects in maintaining the security of national cyberspace. Starting from the 5G network architecture and interfaces, this paper analyzes the underlying security risks faced by the 5G networks and proposes a corresponding solution as an example in terms of the commercial cryptography application practices of the 5G network. Reference | Related Articles | Metrics

Select

Towards a Privacy-preserving Research for AI and Blockchain Integration Journal of Information Security Reserach    2023, 9 (6): 557-.   Abstract （637）      PDF （1307KB）（339）       Knowledge map    Save With the widespread attention and application of artificial intelligence (AI) and blockchain technologies, privacy protection techniques arising from their integration are of notable significance. In addition to protecting the privacy of individuals, these techniques also guarantee the security and dependability of data. This paper initially presents an overview of AI and blockchain, summarizing their combination along with derived privacy protection technologies. It then explores specific application scenarios in data encryption, deidentification, multitier distributed ledgers, and kanonymity methods. Moreover, the paper evaluates five critical aspects of AIblockchainintegration privacy protection systems, including authorization management, access control, data protection, network security, and scalability. Furthermore, it analyzes the deficiencies and their actual cause, offering corresponding suggestions. This research also classifies and summarizes privacy protection techniques based on AIblockchain application scenarios and technical schemes. In conclusion, this paper outlines the future directions of privacy protection technologies emerging from AI and blockchain integration, including enhancing efficiency and security to achieve more comprehensive privacy protection of AI privacy. Reference | Related Articles | Metrics

Select

On the Exploration and Prospect of the Development Path of  Cyberspace Trusted Identity in China Journal of Information Security Reserach    2022, 8 (12): 1236-.   Abstract （604）      PDF （1941KB）（146）       Knowledge map    Save Reference | Related Articles | Metrics

Select

Journal of Information Security Reserach    2023, 9 (E1): 105-.   Abstract （597）      PDF （1450KB）（325）       Knowledge map    Save Reference | Related Articles | Metrics

Select

Journal of Information Security Reserach    2023, 9 (3): 206-.   Abstract （589）      PDF （513KB）（391）       Knowledge map    Save Related Articles | Metrics

Select

Application of Penetration Testing for Industrial Control System Terminals Journal of Information Security Reserach    2023, 9 (4): 313-.   Abstract （531）      PDF （3070KB）（213）       Knowledge map    Save The security of industrial control system terminals is getting crucial with the development of the industrial Internet. How to conduct effective safety tests for industrial control system terminals has become a key problem to be studied and solved urgently. In this paper, the general process of penetration testing is firstly introduced, then the application of penetration testing for industrial control system terminals is examined using improper input validation vulnerability as an example. The method starts from information collection and penetration tools to deeply understand the system input verification. Then, during the stage of the vulnerability discovery, the modeling of the vulnerability to sensitive input is proposed, as well as the seed mutation pattern for the industrial control programs is designed. The experiment demonstrates the effectiveness of the proposed method and the vulnerability widely existed in the industrial control systems. This method also discovers the security threats such as data tampering, denial of service, permission access and malicious script injection caused by the input validation vulnerability. At last, this work provides security suggestions for industrial control network security protection and equipment protection. Reference | Related Articles | Metrics

Select

Research on Content Detection Generated by Large Language Model  and the Mechanism of Bypassing Journal of Information Security Reserach    2023, 9 (6): 524-.   Abstract （504）      PDF （1924KB）（333）       Knowledge map    Save In recent years, there has been a surge in the development of large language models. AI robots like ChatGPT, although they have a largescale security confrontation mechanism inside, attackers can still elaborate questionandanswer patterns to bypass the mechanism, with their help to automatically produce phishing emails and carry out network attacks. In this case, how to identify the text generated by AI robots has also become a hot issue. In order to carry out LLMgenerated content detection experiment, our team collected a certain number of questionandanswer data samples from an Internet social platform and ChatGPT platform, and proposed a series of detection strategies according to different conditions of AI text availability. It includes text similarity analysis based on online controllable AI samples, text data mining based on statistical differences under offline conditions, adversarial analysis based on the LLM generation method under the condition that AI samples are not available, and AI model analysis based on building a classifier by finetuning the target LLM model itself. We calculated and compared the detection capabilities of the analysis engine in each case. On the other hand, we give some antikill techniques against AI text detection engines based on the characteristics of detection strategies, from the perspective of network attack and defense. Reference | Related Articles | Metrics

Select

A Survey of SQL Injection Attack Detection and Defense Technology Journal of Information Security Reserach    2023, 9 (5): 412-.   Abstract （502）      PDF （2612KB）（366）       Knowledge map    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

Select

Journal of Information Security Reserach    2022, 8 (9): 856-.   Abstract （469）      PDF （391KB）（290）       Knowledge map    Save Related Articles | Metrics

Select

Automated Vulnerability Mining and Attack Detection Journal of Information Security Reserach    2022, 8 (7): 630-.   Abstract （459）      PDF （434KB）（363）       Knowledge map    Save Related Articles | Metrics

Select

Research on Network Security Governance and Response of  Largescale AI Model Journal of Information Security Reserach    2023, 9 (6): 551-.   Abstract （458）      PDF （1101KB）（433）       Knowledge map    Save With the continuous development of artificial intelligence technology, largescale AI model technology has become an important research direction in the field of artificial intelligence. The publication of ChatGPT4.0 and ERNIE Bot has rapidly promoted the development and application of this technology. However, the emergence of largescale AI model technology has also brought new challenges to network security. This paper will start with the definition, characteristics and application of largescale AI model technology, and analyze the network security situation under largescale AI model technology. The network security governance framework of largescale AI model is proposed, and the given steps can provide reference for network security work of largescale AI model. Reference | Related Articles | Metrics

Select

Key Points and Practice of Compliance Assessment for Government Data Security Journal of Information Security Reserach    2022, 8 (11): 1050-.   Abstract （453）      PDF （719KB）（386）       Knowledge map    Save With the development of digital government, the security of government data has become a crucial task. The state attaches great importance to the security risk prevention of government data, and has issued a series of laws, regulations and policy documents, which put forward clear requirements for strengthening the security management of government data. Based on the requirements of government data security compliance, this article proposes the evaluation method and index system of compliance assessment for government data security, which will provide reference for the manager of government data to carry out government data security compliance assessment. Reference | Related Articles | Metrics

Select

Research on Memorycorruption Vulnerability Defense Methods  Based on Memory Protection Technology Journal of Information Security Reserach    2022, 8 (7): 694-.   Abstract （452）      PDF （1030KB）（234）       Knowledge map    Save Since its outbreak of COVID19 in the world, the process of digital transformation has been further accelerated in all sectors around the world. With the increasing value of information assets, information security problems follow. Vulnerability attacks are the root cause of frequent security incidents in recent years. Vulnerability defense ability directly affects the security of the system. How to prevent vulnerability exploitation without patches has become an urgent need. Vulnerability exploitation defense has also become an important research content in the field of attack and defense confrontation of information security. This paper studies the binary memorycorruption vulnerability defense methods and puts forward a new method to deal with the increasing vulnerability attacks.Key words memory protection technology; memorycorruption vulnerability; network security; behavior monitoring; vulnerability defense; endpoint security Related Articles | Metrics

Select

Data Security Governance Practices Journal of Information Security Reserach    2022, 8 (11): 1069-.   Abstract （440）      PDF （5897KB）（355）       Knowledge map    Save Data security governance has been written into the Data Security Law of the People’s Republic of China. At the same time, data security governance is also one of the key points in the construction of systematic network security. This paper analyzes the data security governance concepts of Gantner and Microsoft, combines enterprise architecture, stakeholder theory, data flow security assessment, maturity security assessment and other methodologies, forms a set of data security governance concepts, and designs a data security management and operation platform for dynamic supervision and data security operation of data security governance indicators. Since 2018, this methodology and platform have been put into practice in the project to solve the construction and optimization of users’ data management and defense system. Reference | Related Articles | Metrics

Select

Journal of Information Security Reserach    2022, 8 (8): 734-.   Abstract （436）      PDF （422KB）（336）       Knowledge map    Save Related Articles | Metrics

Select

Journal of Information Security Reserach    2022, 8 (8): 812-.   Abstract （422）      PDF （4751KB）（254）       Knowledge map    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

Select

Malicious Client Detection and Defense Method for Federated Learning Journal of Information Security Reserach    2024, 10 (2): 163-.   Abstract （408）      PDF （806KB）（239）       Knowledge map    Save Federated learning allows participating clients to collaborate in training machine learning models without sharing their private data. Since the central server cannot control the behavior of clients, malicious clients may corrupt the global model by sending manipulated local gradient updates, and there may also be unreliable clients with low data quality but some value. To address the above problems, this paper proposes FedMDD,a defense approach for malicious client detection and defense for federated learning, to process detected malicious and unreliable clients in different ways based on local gradient updates, while defending against symbol flipping, additive noise, single label flipping, multilabel flipping, and backdoor attacks. Four baseline algorithms are compared for two datasets, and the experimental results show that FedMDD can successfully defend against various types of attacks in a training environment containing 50% malicious clients and 10% unreliable clients, with better results in both improving model testing accuracy and reducing backdoor accuracy. Related Articles | Metrics

Select

Survey of Coverage-guided Grey-box Fuzzing Journal of Information Security Reserach    2022, 8 (7): 643-.   Abstract （402）      PDF （1745KB）（294）       Knowledge map    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

Select

Research on the Progress of Crossborder Data Flow Governance Journal of Information Security Reserach    2023, 9 (7): 624-.   Abstract （391）      PDF （1036KB）（183）       Knowledge map    Save While promoting the sharing of global data resources, the crossborder data flow will inevitably threaten data sovereignty and national security. The competition for the right to speak in international data with crossborder data flow governance as the game will become the focus of competition in the international community in the future. This paper introduces the background knowledge and constraints of crossborder data flow, investigates and compares the crossborder data flow governance models of the United States, the European Union, Russia, Japan, and Australia, and analyzes the current policy status and challenges of crossborder data flow governance in our country, on this basis, countermeasures and suggestions are proposed for the governance of crossborder data flow in our country from the perspective of data sovereignty, including promoting the classification supervision of crossborder data flow, innovating and developing crossborder data flow governance models, improving countermeasures against extraterritorial “longarm jurisdiction”, and actively participating in and leading the formulation of international governance rules. Reference | Related Articles | Metrics

Select

Safety Management of Electronic Display Screen in  Public Areas Journal of Information Security Reserach    2023, 9 (4): 397-.   Abstract （388）      PDF （629KB）（165）       Knowledge map    Save Reference | Related Articles | Metrics

Select

Survey of Network Intrusion Detection Based on Deep Learning Journal of Information Security Reserach    2022, 8 (12): 1163-.   Abstract （386）      PDF （2421KB）（276）       Knowledge map    Save The rapid development of the Internet not only brings great convenience to users, but also causes many security incidents. With the increasing number of network attacks such as zeroday vulnerabilities and encryption attacks, the network security situation is becoming more and more serious. Intrusion detection is an important means of network attack detection. In recent years, with the continuous development of deep learning technology, intrusion detection system based on deep learning is gradually becoming a research hotspot in the field of network security. This paper introduces recent work on network intrusion detection using deep learning technology based on extensive investigation of literature. Firstly, it briefly summarizes the current network security situation and traditional intrusion detection technologies. Then, several deep learning models commonly used in network intrusion detection system are introduced. Then it summarizes the commonly used data preprocessing techniques, data sets and evaluation indicators in deep learning. Then from the perspective of practical application, it introduces the specific application of deep learning model in network intrusion detection system. Finally, the problems in the current research process are discussed, and the future development direction is put forward. Reference | Related Articles | Metrics

Select

Journal of Information Security Reserach    2024, 10 (E1): 236-.   Abstract （383）      PDF （796KB）（306）       Knowledge map    Save Reference | Related Articles | Metrics

Select

Research on the Application of Commercial Cryptography to Cloud Computing Journal of Information Security Reserach    2023, 9 (4): 375-.   Abstract （366）      PDF （3447KB）（325）       Knowledge map    Save Cloud computing, as a new information processing method, enables users to access information and communication resource services through the network, and it has become an inevitable trend in the development of information technology industry. Users, data, and information resources are highly concentrated, highly dependent on the continuity of cloud platform services, and the scalability of virtualized resources bring inevitable security risks to cloud computing., and the scalability of virtualized resources bring inevitable security risks to cloud computing. Therefore, how to eliminate the security risks of cloud computing by using commercial cryptography technology has become the current research hotspot. This paper starts from the cloud computing network architecture, anlyzes the cryptography application requirements of cloud computing. The paper proposes the corresponding commercial cryptography application scheme for cloud computing scenarios on this basis. The research results provide a theoretical guidance and reference for the application practice of commercial cryptography in cloud computing scenarios, and are expected to solve the key problems of cloud computing security. Reference | Related Articles | Metrics

Select

Journal of Information Security Reserach    2024, 10 (E2): 105-.   Abstract （363）      PDF （929KB）（241）       Knowledge map    Save Reference | Related Articles | Metrics

Select

Key Technologies and Research Prospects of Privacy Computing Journal of Information Security Reserach    2023, 9 (8): 714-.   Abstract （348）      PDF （1814KB）（254）       Knowledge map    Save Privacy computing, as an important technical means taking into account both data circulation and privacy protection, can effectively break the “data island” barriers while ensuring data security, it enables open data sharing, and promotes the deep mining and use of data and crossdomain integration. In this paper, the background knowledge, basic concepts and architecture of privacy computing were introduced, the basic concepts of three key technologies of privacy computing, including secure multiparty computation, federated learning and trusted execution environment were elaborated, and studies on the existing privacy security was conducted, a multidimensional comparison and summarization of the differences of the three key technologies were made. On this basis, the future research direction of privacy computing is prospected from the technical integration of privacy computing with blockchain, deep learning and knowledge graph. Reference | Related Articles | Metrics

Select

Journal of Information Security Reserach    2023, 9 (6): 498-.   Abstract （347）      PDF （472KB）（427）       Knowledge map    Save Related Articles | Metrics

Select

Federated Foundation Model Finetuning Based on Differential Privacy#br# #br# Journal of Information Security Reserach    2024, 10 (7): 616-.   Abstract （342）      PDF （1752KB）（198）       Knowledge map    Save As the availability of private data decreases, large model finetuning based on federated learning has become a research area of great concern. Although federated learning itself has a certain degree of privacy protection, privacy security issues such as gradient leakage attacks and embedding inversion attacks on large models still threaten the sensitive information of participants. In the current context of increasing awareness of privacy protection, these potential privacy risks have significantly hindered the promotion of large model finetuning based on federated learning in practical applications. Therefore, this paper proposes a federated large model embedding differential privacy control algorithm, which adds controllable random noise to the embedded model of the large model during efficient parameter finetuning process through a global and local dual privacy control mechanism to enhance the privacy protection ability of federated learning based large model parameter finetuning. In addition, this paper demonstrates the privacy protection effect of this algorithm in large model finetuning through experimental comparisons of different federation settings, and verifies the feasibility of the algorithm through performance comparison experiments between centralization and federation. Reference | Related Articles | Metrics

Select

A Survey of Data Security Sharing Technology Development and  Its Application in Power Domain Journal of Information Security Reserach    2023, 9 (3): 208-.   Abstract （340）      PDF （2019KB）（240）       Knowledge map    Save The circulation, sharing and collaborative application of data elements are the core elements of data element market cultivation in the digital era, and data security sharing technology can effectively realize the secure sharing of data and avoid the phenomenon of “data silos” and privacy leakage. This paper presents a comprehensive review of the latest research achievements and progress of data security sharing technologies in this field. First of all, we outline the development and evolution of data security sharing technologies, and then compare and analyze existing data security sharing solutions in terms of technical features, problem solving, advantages and disadvantages, and summarize the key technologies they rely on and the risks and challenges they face. Secondly, we discuss the application of data security sharing technologies in typical scenarios in the energy and power fields, such as power energy trading, power internet of things, and electric vehicles, providing new ideas and insights for data compliance and governance in the energy and power fields. Finally, the future research directions and development prospects of data security sharing technology applications in the energy and power domain are foreseen. Reference | Related Articles | Metrics

Select

Journal of Information Security Reserach    2024, 10 (E1): 246-.   Abstract （339）      PDF （1562KB）（209）       Knowledge map    Save Reference | Related Articles | Metrics

Select

Journal of Information Security Reserach    2022, 8 (8): 845-.   Abstract （331）      PDF （1967KB）（227）       Knowledge map    Save Aiming at the problems of complex sources, difficult to understand and share security threat intelligence, this paper realizes deep learning of threat intelligence features based on restricted Boltzmann machine, which maps the original threat intelligence features from high dimensional space to low dimensional space layer by layer, and constructs the cyberspace security threat knowledge map. By using the cyberspace security threat knowledge map, and combining with the current context, the path evolution and tracing of security threats are carried out through event flow processing to accurately perceive cyberspace security threats. The experiment verifies the feasibility of constructing the cyberspace security threat knowledge map, and verifies the security threat perception method based on the knowledge map is more suitable for the perception of highintensity security threats by comparing with traditional threat detection methods. Related Articles | Metrics

Select

Journal of Information Security Reserach    2022, 8 (8): 831-.   Abstract （325）      PDF （719KB）（297）       Knowledge map    Save At present, open source has become one of the best organizing methods for human superlargescale intellectual collaboration, and has also become the "main battlefield" of technological innovation, ushering in great development worldwide. At the same time, open source software has also become a mature target for software supply chain attacks, facing security vulnerabilities, intellectual property rights, open source regulation and other risks. This paper analyzes the current security situation and risks of open source software supply chain, puts forward open source software development security solutions, and puts forward suggestions for the development of open source software supply chain. Related Articles | Metrics

Select

Research on Several Issues in the Construction of Network Trusted  Identity System Journal of Information Security Reserach    2022, 8 (9): 871-.   Abstract （315）      PDF （2082KB）（148）       Knowledge map    Save This paper works through a series of concepts related to “network identity”, extends the experience and ideas of network identity management from the ways and methods of real social identity management, analyzes the four basic stages involved in network identity life cycle management and the key problems to be solved, and puts forward the reference architecture of network trusted identity system and its system functional structure, It also puts forward relevant suggestions to promote the construction and application of network trusted identity system in China. Reference | Related Articles | Metrics

Select

A Novel Blockchain Privacy Preserving Scheme Based on Paillier  and FO Commitment Journal of Information Security Reserach    2023, 9 (4): 306-.   Abstract （311）      PDF （934KB）（226）       Knowledge map    Save The blockchain is a shared database with excellent characteristics such as high decentralization and traceability. However, data leakage is still a big problem for blockchain transactions. To order to solve the problem, this paper introduces Paillier homomorphic encryption with variable k (KPH), a privacy protection strategy that hides transaction information by the public key encryption algorithm RSA, performs zeroknowledge proof on the legitimacy of the transaction amount with FO commitment, and updates the transaction amount using the enhanced Paillier semihomomorphic encryption algorithm and verifies the transaction using the FO commitment. Unlike the typical Paillier algorithm, the KPH scheme’s Paillier algorithm includes the variable k and combines the L function and the Chinese remainder theorem to reduce the time complexity from O(|n|2+e) to O(logn), making the algorithm decryption process more efficient. Reference | Related Articles | Metrics

Select

Journal of Information Security Reserach    2022, 8 (8): 751-.   Abstract （309）      PDF （2071KB）（335）       Knowledge map    Save ATT&CK framework, as an attack perspective framework of network security in recent years, has attracted extensive research in the industry. This paper introduces the existing network security evaluation and detection technologies based on ATT&CK framework, and gives its own research results on this basis. In terms of evaluation, an automatic evaluation system based on ATT&CK framework is proposed. In terms of detection, the data source standardization method, attack analysis framework and attack chain analysis framework based on knowledge graph which are required by detection based on ATT&CK framework are proposed. This paper provides specific idea and implementation scheme for the application of ATT&CK framework in network security evaluation and detection. Related Articles | Metrics

Select

Journal of Information Security Reserach    2022, 8 (8): 768-.   Abstract （298）      PDF （1781KB）（273）       Knowledge map    Save Docker is widely used in network application systems. However, there are not enough corresponding protection measures for the relatively low frequency but fatal escape problem. In order to reduce the harm of the docker escape problems, CFMAC (container based on fuzzy mandatory access control) model is proposed to reinforce the security of the Docker container. The model uses mandatory access control to restrict the attacker's access after Evasion Attacks. As well as, in order to solve the problem of hard to determine the entity security level and strong subjectivity in mandatory access control, fuzzy clustering analysis and risk matrix analysis are combined to divide the subject and object into three levels: secret, general and public, to intercept access and enter security verification by LSM(Linux security model). The test results show that the model can successfully restrict suspicious processes to access files. Related Articles | Metrics

Select

Research on the Integration of Full Lifecycle Data Security Management and Artificial Intelligence Technology#br# Journal of Information Security Reserach    2023, 9 (6): 543-.   Abstract （297）      PDF （1143KB）（260）       Knowledge map    Save With data becoming a new production factor, China has elevated data security to a national strategic level. With the promotion of a new round of technological revolution and the deepening of digital transformation, the artificial intelligence technology has increasing development potential, and gradually empowers the field of data security management actively. Firstly, the paper introduces the concept and significance of data security lifecycle management, analyzes the security risks faced by data in various stages of the lifecycle, and further discusses the problems and challenges faced by traditional data security management technologies in the context of massive data processing and upgraded attack methods. Then, the paper introduces the potential advantages of artificial intelligence in solving these problems and challenges, and summarizes the current mature data security management technologies based on artificial energy and typical application scenarios. Finally, the paper provides an outlook on the future development trends of artificial intelligence technologies in the field of data security management. This paper aims to provide useful references for researchers and practitioners in the field of data security management, and promote the innovation and application of artificial intelligence in the field of data security management technology. Reference | Related Articles | Metrics

Select

ChatGPT’s Security Threaten Research Journal of Information Security Reserach    2023, 9 (6): 533-.   Abstract （296）      PDF （1801KB）（264）       Knowledge map    Save With the rapid development of deep learning technology and natural language processing technology, the large language model represented by ChatGPT came into being. However, while showing surprising capabilities in many fields, ChatgPT also exposed many security threats, which aroused the concerns of academia and industry. This paper first introduces the development history, working mode, and training methods of ChatGPT and its series models, then summarizes and analyzes various current security problems that ChatGPT may encounter and divides it into two levels: user and model. Then, countermeasures and solutions are proposed according to the characteristics of ChatGPT at each stage. Finally, this paper looks forward to developing a safe and trusted ChatGPT and a large language model. Reference | Related Articles | Metrics

Select

Journal of Information Security Reserach    2022, 8 (6): 545-.   Abstract （293）      PDF （1253KB）（150）       Knowledge map    Save With the rapid development of automotive intelligence, onboard system changes the landscape of vehicle behavior automation. Various firmware and hardware devices can interact or exchange information with the onboard intelligent system. The Internet of vehicles carries the automatic control of software, ECU and hardware via the onboard intelligent system. Instate providing users with daytoday driving functionality, the onboard system been evolved and increase its complexity. There is no clear boundary between system security and functional safety. This paper gives an overview of the onboard intelligent system of the Internet of vehicles based on experimental modeling. It also emphasizes that under the scenario of the Internet of vehicles, the vulnerability and system failure of the intelligent vehicle system will directly affect the functional safety, which means it can threaten the safety of passengers. Therefore, the onboard system security of the Internet of vehicles becomes more and more important. This paper discusses the relationship between system security and functional safety in the Internet of vehicles based on an existing issue. In order to locate the actual system security in the Internet of vehicles, the existing defense indicates that the importance to find a balance point between vehicle performance and system security within the limited resource, this paper proposed a method about prereinforcement learning defense mechanism based on pseudo defense.Key words Internet of vehicles security; endogenous security; mimicry defense; reinforcement learning; information system security Related Articles | Metrics

Select

A Review of Algorithmic Risk and Its Governance in China#br# #br# Journal of Information Security Reserach    2024, 10 (2): 114-.   Abstract （288）      PDF （1781KB）（182）       Knowledge map    Save In the era of digital intelligence, algorithms pervade every corner of human society. While algorithms drive the transformation towards digitization and intelligence, they also give rise to a series of issues, necessitating effective governance of increasing algorithmic risks. Firstly, algorithmic risks are categorized into four fields: law and justice, politics and governance, information dissemination and business and economy. Then the formation mechanisms of algorithmic risk are analyzed, encompassing algorithm black box, algorithm discrimination and power alienation. Finally, a governance strategy framework is proposed, consisting of three paths: technology regulation, power and responsibility normative, and ecological optimization. The research systematically presents the progress and development trend of algorithmic risk and its governance in China, providing reference for advancing the theoretical research and system construction inalgorithmic risk governance. Reference | Related Articles | Metrics