Federated Learning(FL)enables joint training over distributed devices without data exchange but is highly vulnerable to attacks by adversaries in the form of model poisoning and malicious update injection.This work pr...Federated Learning(FL)enables joint training over distributed devices without data exchange but is highly vulnerable to attacks by adversaries in the form of model poisoning and malicious update injection.This work proposes Secured-FL,a blockchain-based defensive framework that combines smart contract-based authentication,clustering-driven outlier elimination,and dynamic threshold adjustment to defend against adversarial attacks.The framework was implemented on a private Ethereum network with a Proof-of-Authority consensus algorithm to ensure tamper-resistant and auditable model updates.Large-scale simulation on the Cyber Data dataset,under up to 50%malicious client settings,demonstrates Secured-FL achieves 6%-12%higher accuracy,9%-15%lower latency,and approximately 14%less computational expense compared to the PPSS benchmark framework.Additional tests,including confusion matrices,ROC and Precision-Recall curves,and ablation tests,confirm the interpretability and robustness of the defense.Tests for scalability also show consistent performance up to 500 clients,affirming appropriateness to reasonably large deployments.These results make Secured-FL a feasible,adversarially resilient FL paradigm with promising potential for application in smart cities,medicine,and other mission-critical IoT deployments.展开更多
Although Named Entity Recognition(NER)in cybersecurity has historically concentrated on threat intelligence,vital security data can be found in a variety of sources,such as open-source intelligence and unprocessed too...Although Named Entity Recognition(NER)in cybersecurity has historically concentrated on threat intelligence,vital security data can be found in a variety of sources,such as open-source intelligence and unprocessed tool outputs.When dealing with technical language,the coexistence of structured and unstructured data poses serious issues for traditional BERT-based techniques.We introduce a three-phase approach for improved NER inmulti-source cybersecurity data that makes use of large language models(LLMs).To ensure thorough entity coverage,our method starts with an identification module that uses dynamic prompting techniques.To lessen hallucinations,the extraction module uses confidence-based self-assessment and cross-checking using regex validation.The tagging module links to knowledge bases for contextual validation and uses SecureBERT in conjunction with conditional random fields to detect entity boundaries precisely.Our framework creates efficient natural language segments by utilizing decoderbased LLMs with 10B parameters.When compared to baseline SecureBERT implementations,evaluation across four cybersecurity data sources shows notable gains,with a 9.4%–25.21%greater recall and a 6.38%–17.3%better F1-score.Our refined model matches larger models and achieves 2.6%–4.9%better F1-score for technical phrase recognition than the state-of-the-art alternatives Claude 3.5 Sonnet,Llama3-8B,and Mixtral-7B.The three-stage architecture identification-extraction-tagging pipeline tackles important cybersecurity NER issues.Through effective architectures,these developments preserve deployability while setting a new standard for entity extraction in challenging security scenarios.The findings show how specific enhancements in hybrid recognition,validation procedures,and prompt engineering raise NER performance above monolithic LLM approaches in cybersecurity applications,especially for technical entity extraction fromheterogeneous sourceswhere conventional techniques fall short.Because of itsmodular nature,the framework can be upgraded at the component level as new methods are developed.展开更多
Traditional steganography conceals information by modifying cover data,but steganalysis tools easily detect such alterations.While deep learning-based steganography often involves high training costs and complex deplo...Traditional steganography conceals information by modifying cover data,but steganalysis tools easily detect such alterations.While deep learning-based steganography often involves high training costs and complex deployment.Diffusion model-based methods face security vulnerabilities,particularly due to potential information leakage during generation.We propose a fixed neural network image steganography framework based on secure diffu-sion models to address these challenges.Unlike conventional approaches,our method minimizes cover modifications through neural network optimization,achieving superior steganographic performance in human visual perception and computer vision analyses.The cover images are generated in an anime style using state-of-the-art diffusion models,ensuring the transmitted images appear more natural.This study introduces fixed neural network technology that allows senders to transmit only minimal critical information alongside stego-images.Recipients can accurately reconstruct secret images using this compact data,significantly reducing transmission overhead compared to conventional deep steganography.Furthermore,our framework innovatively integrates ElGamal,a cryptographic algorithm,to protect critical information during transmission,enhancing overall system security and ensuring end-to-end information protection.This dual optimization of payload reduction and cryptographic reinforcement establishes a new paradigm for secure and efficient image steganography.展开更多
As a key node of modern transportation network,the informationization management of road tunnels is crucial to ensure the operation safety and traffic efficiency.However,the existing tunnel vehicle modeling methods ge...As a key node of modern transportation network,the informationization management of road tunnels is crucial to ensure the operation safety and traffic efficiency.However,the existing tunnel vehicle modeling methods generally have problems such as insufficient 3D scene description capability and low dynamic update efficiency,which are difficult to meet the demand of real-time accurate management.For this reason,this paper proposes a vehicle twin modeling method for road tunnels.This approach starts from the actual management needs,and supports multi-level dynamic modeling from vehicle type,size to color by constructing a vehicle model library that can be flexibly invoked;at the same time,semantic constraint rules with geometric layout,behavioral attributes,and spatial relationships are designed to ensure that the virtual model matches with the real model with a high degree of similarity;ultimately,the prototype system is constructed and the case region is selected for the case study,and the dynamic vehicle status in the tunnel is realized by integrating real-time monitoring data with semantic constraints for precise virtual-real mapping.Finally,the prototype system is constructed and case experiments are conducted in selected case areas,which are combined with real-time monitoring data to realize dynamic updating and three-dimensional visualization of vehicle states in tunnels.The experiments show that the proposed method can run smoothly with an average rendering efficiency of 17.70 ms while guaranteeing the modeling accuracy(composite similarity of 0.867),which significantly improves the real-time and intuitive tunnel management.The research results provide reliable technical support for intelligent operation and emergency response of road tunnels,and offer new ideas for digital twin modeling of complex scenes.展开更多
Software security poses substantial risks to our society because software has become part of our life. Numerous techniques have been proposed to resolve or mitigate the impact of software security issues. Among them, ...Software security poses substantial risks to our society because software has become part of our life. Numerous techniques have been proposed to resolve or mitigate the impact of software security issues. Among them, software testing and analysis are two of the critical methods, which significantly benefit from the advancements in deep learning technologies. Due to the successful use of deep learning in software security, recently,researchers have explored the potential of using large language models(LLMs) in this area. In this paper, we systematically review the results focusing on LLMs in software security. We analyze the topics of fuzzing, unit test, program repair, bug reproduction, data-driven bug detection, and bug triage. We deconstruct these techniques into several stages and analyze how LLMs can be used in the stages. We also discuss the future directions of using LLMs in software security, including the future directions for the existing use of LLMs and extensions from conventional deep learning research.展开更多
ChatGPT is a powerful artificial intelligence(AI)language model that has demonstrated significant improvements in various natural language processing(NLP) tasks. However, like any technology, it presents potential sec...ChatGPT is a powerful artificial intelligence(AI)language model that has demonstrated significant improvements in various natural language processing(NLP) tasks. However, like any technology, it presents potential security risks that need to be carefully evaluated and addressed. In this survey, we provide an overview of the current state of research on security of using ChatGPT, with aspects of bias, disinformation, ethics, misuse,attacks and privacy. We review and discuss the literature on these topics and highlight open research questions and future directions.Through this survey, we aim to contribute to the academic discourse on AI security, enriching the understanding of potential risks and mitigations. We anticipate that this survey will be valuable for various stakeholders involved in AI development and usage, including AI researchers, developers, policy makers, and end-users.展开更多
The integration of artificial intelligence(AI)technology,particularly large language models(LLMs),has become essential across various sectors due to their advanced language comprehension and generation capabilities.De...The integration of artificial intelligence(AI)technology,particularly large language models(LLMs),has become essential across various sectors due to their advanced language comprehension and generation capabilities.Despite their transformative impact in fields such as machine translation and intelligent dialogue systems,LLMs face significant challenges.These challenges include safety,security,and privacy concerns that undermine their trustworthiness and effectiveness,such as hallucinations,backdoor attacks,and privacy leakage.Previous works often conflated safety issues with security concerns.In contrast,our study provides clearer and more reasonable definitions for safety,security,and privacy within the context of LLMs.Building on these definitions,we provide a comprehensive overview of the vulnerabilities and defense mechanisms related to safety,security,and privacy in LLMs.Additionally,we explore the unique research challenges posed by LLMs and suggest potential avenues for future research,aiming to enhance the robustness and reliability of LLMs in the face of emerging threats.展开更多
Traditional multi-level security(MLS)systems have the defect of centralizing authorized facilities,which is difficult to meet the security requirements of modern distributed peer-to-peer network architecture.Blockchai...Traditional multi-level security(MLS)systems have the defect of centralizing authorized facilities,which is difficult to meet the security requirements of modern distributed peer-to-peer network architecture.Blockchain is widely used in the field of access control with its decentralization,traceability and non-defective modification.Combining the blockchain technology and the Bell-LaPadula model,we propose a new access control model,named BCBLPM,for MLS environment.The“multi-chain”blockchain architecture is used for dividing resources into isolated access domains,providing a fine-grained data protection mechanism.The access control policies are implemented by smart contracts deployed in each access domain,so that the side chains of different access domains storage access records from outside and maintain the integrity of the records.Finally,we implement the BC-BLPM prototype system using the Hyperledger Fabric.The experimental and analytical results show that the model can adapt well to the needs of multi-level security environment,and it has the feasibility of application in actual scenarios.展开更多
To give concurrent consideration both the efficiency and the security(intensity of intractable problem) in the standard model,a chosen ciphertext secure identity-based broadcast encryption is proposed.Against the chos...To give concurrent consideration both the efficiency and the security(intensity of intractable problem) in the standard model,a chosen ciphertext secure identity-based broadcast encryption is proposed.Against the chosen ciphertext security model,by using identity(ID) sequence and adding additional information in ciphertext,the self-adaptive chosen identity security(the full security) and the chosen ciphertext security are gained simultaneously.The reduction of scheme's security is the decisional bilinear Diffie-Hellman(BDH) intractable assumption,and the proof of security shows that the proposed scheme is indistinguishable against adaptive chosen ciphertext attacks in the standard model under the decisional BDH intractable assumption.So the security level is improved,and it is suitable for higher security environment.展开更多
In view of the security weakness in resisting the active attacks by malicious nodes in mobile ad hoc networks,the trust metric is introduced to defend those attacks by loading a trust model on the previously proposed ...In view of the security weakness in resisting the active attacks by malicious nodes in mobile ad hoc networks,the trust metric is introduced to defend those attacks by loading a trust model on the previously proposed Distance-Based LAR.The improved Secure Trust-based Location-Aided Routing algorithm utilizes direct trust and recommendation trust to prevent malicious nodes with low trust values from joining the forwarding.Simulation results reveal that ST-LAR can resist attacks by malicious nodes effectively;furthermore,it also achieves better performance than DBLAR in terms of average end-to-end delay,packet delivery success ratio and throughput.展开更多
Recently,the 2025 Central Conference on Work Related to Neighboring Countries was held in Beijing.As an important theoretical innovation,the conference emphasized for the first time pursuing“the model of security for...Recently,the 2025 Central Conference on Work Related to Neighboring Countries was held in Beijing.As an important theoretical innovation,the conference emphasized for the first time pursuing“the model of security for Asia that features sharing weal and woe,seeking common ground while shelving differences,and prioritizing dialogue and consultation.”1 This fully demonstrates that China prioritizes neighborhood on its diplomatic agenda,regards security and stability in its neighborhood as a core strategic support,and is ready to collaborate with neighboring countries for a future of shared peace,development,and prosperity.展开更多
In response to the current gaps in ef-fective proactive defense methods within applica-tion security and the limited integration of security components with applications,this paper proposes a biomimetic security model...In response to the current gaps in ef-fective proactive defense methods within applica-tion security and the limited integration of security components with applications,this paper proposes a biomimetic security model,called NeuroShield,specifically designed for web applications.Inspired by the“perception-strategy-effect-feedback”mechanism of the human nervous control system,the model inte-grates biomimetic elements akin of neural receptors and effectors into applications.This integration fa-cilitates a multifaceted approach to security:enabling data introspection for detailed perception and regula-tion of application behavior,providing proactive de-fense capabilities to detect and block security risks in real-time,and incorporating feedback optimization to continuously adjust and enhance security strategies based on prevailing conditions.Experimental results affirm the efficacy of this neural control mechanism-based biomimetic security model,demonstrating a proactive defense success rate exceeding 95%,thereby offering a theoretical and structural foundation for biomimetic immunity in web applications.展开更多
Security is the cor nerstone of a country's peace and stability and the prerequisite for its survival and development.All countries around the world regard security as their top priority.Since most Asian countries...Security is the cor nerstone of a country's peace and stability and the prerequisite for its survival and development.All countries around the world regard security as their top priority.Since most Asian countries suffered from colonial aggression and plundering for a long time in history,they as a whole attach special importance to national security.展开更多
The Internet of Things (IoT) and edge-assisted networking infrastructures are capable of bringing data processing and accessibility services locally at the respective edge rather than at a centralized module. These in...The Internet of Things (IoT) and edge-assisted networking infrastructures are capable of bringing data processing and accessibility services locally at the respective edge rather than at a centralized module. These infrastructures are very effective in providing a fast response to the respective queries of the requesting modules, but their distributed nature has introduced other problems such as security and privacy. To address these problems, various security-assisted communication mechanisms have been developed to safeguard every active module, i.e., devices and edges, from every possible vulnerability in the IoT. However, these methodologies have neglected one of the critical issues, which is the prediction of fraudulent devices, i.e., adversaries, preferably as early as possible in the IoT. In this paper, a hybrid communication mechanism is presented where the Hidden Markov Model (HMM) predicts the legitimacy of the requesting device (both source and destination), and the Advanced Encryption Standard (AES) safeguards the reliability of the transmitted data over a shared communication medium, preferably through a secret shared key, i.e., , and timestamp information. A device becomes trusted if it has passed both evaluation levels, i.e., HMM and message decryption, within a stipulated time interval. The proposed hybrid, along with existing state-of-the-art approaches, has been simulated in the realistic environment of the IoT to verify the security measures. These evaluations were carried out in the presence of intruders capable of launching various attacks simultaneously, such as man-in-the-middle, device impersonations, and masquerading attacks. Moreover, the proposed approach has been proven to be more effective than existing state-of-the-art approaches due to its exceptional performance in communication, processing, and storage overheads, i.e., 13%, 19%, and 16%, respectively. Finally, the proposed hybrid approach is pruned against well-known security attacks in the IoT.展开更多
Processing police incident data in public security involves complex natural language processing(NLP)tasks,including information extraction.This data contains extensive entity information—such as people,locations,and ...Processing police incident data in public security involves complex natural language processing(NLP)tasks,including information extraction.This data contains extensive entity information—such as people,locations,and events—while also involving reasoning tasks like personnel classification,relationship judgment,and implicit inference.Moreover,utilizing models for extracting information from police incident data poses a significant challenge—data scarcity,which limits the effectiveness of traditional rule-based and machine-learning methods.To address these,we propose TIPS.In collaboration with public security experts,we used de-identified police incident data to create templates that enable large language models(LLMs)to populate data slots and generate simulated data,enhancing data density and diversity.We then designed schemas to efficiently manage complex extraction and reasoning tasks,constructing a high-quality dataset and fine-tuning multiple open-source LLMs.Experiments showed that the fine-tuned ChatGLM-4-9B model achieved an F1 score of 87.14%,nearly 30%higher than the base model,significantly reducing error rates.Manual corrections further improved performance by 9.39%.This study demonstrates that combining largescale pre-trained models with limited high-quality domain-specific data can greatly enhance information extraction in low-resource environments,offering a new approach for intelligent public security applications.展开更多
Large models,such as large language models(LLMs),vision-language models(VLMs),and multimodal agents,have become key elements in artificial intelli⁃gence(AI)systems.Their rapid development has greatly improved percepti...Large models,such as large language models(LLMs),vision-language models(VLMs),and multimodal agents,have become key elements in artificial intelli⁃gence(AI)systems.Their rapid development has greatly improved perception,generation,and decision-making in various fields.However,their vast scale and complexity bring about new security challenges.Issues such as backdoor vulnerabilities during training,jailbreaking in multimodal rea⁃soning,and data provenance and copyright auditing have made security a critical focus for both academia and industry.展开更多
A multilevel secure relation hierarchical data model for multilevel secure database is extended from the relation hierarchical data model in single level environment in this paper. Based on the model, an upper lowe...A multilevel secure relation hierarchical data model for multilevel secure database is extended from the relation hierarchical data model in single level environment in this paper. Based on the model, an upper lower layer relationalintegrity is presented after we analyze and eliminate the covert channels caused by the database integrity.Two SQL statements are extended to process polyinstantiation in the multilevel secure environment.The system based on the multilevel secure relation hierarchical data model is capable of integratively storing and manipulating complicated objects ( e.g. , multilevel spatial data) and conventional data ( e.g. , integer, real number and character string) in multilevel secure database.展开更多
Accurate time synchronization is fundamental to the correct and efficient operation of Wireless Sensor Networks(WSNs),especially in security-critical,time-sensitive applications.However,most existing protocols degrade...Accurate time synchronization is fundamental to the correct and efficient operation of Wireless Sensor Networks(WSNs),especially in security-critical,time-sensitive applications.However,most existing protocols degrade substantially under malicious interference.We introduce iSTSP,an Intelligent and Secure Time Synchronization Protocol that implements a four-stage defense pipeline to ensure robust,precise synchronization even in hostile environments:(1)trust preprocessing that filters node participation using behavioral trust scoring;(2)anomaly isolation employing a lightweight autoencoder to detect and excise malicious nodes in real time;(3)reliability-weighted consensus that prioritizes high-trust nodes during time aggregation;and(4)convergence-optimized synchronization that dynamically adjusts parameters using theoretical stability bounds.We provide rigorous convergence analysis including a closed-form expression for convergence time,and validate the protocol through both simulations and realworld experiments on a controlled 16-node testbed.Under Sybil attacks with five malicious nodes within this testbed,iSTSP maintains synchronization error increases under 12%and achieves a rapid convergence.Compared to state-ofthe-art protocols like TPSN,SE-FTSP,and MMAR-CTS,iSTSP offers 60%faster detection,broader threat coverage,and more than 7 times lower synchronization error,with a modest 9.3%energy overhead over 8 h.We argue this is an acceptable trade-off for mission-critical deployments requiring guaranteed security.These findings demonstrate iSTSP’s potential as a reliable solution for secure WSN synchronization and motivate future work on large-scale IoT deployments and integration with energy-efficient communication protocols.展开更多
Efficiency and scalability are still the bottleneck for secure multi-party computation geometry （SMCG）. In this work a secure planar convex hull （SPCH） protocol for large-scaled point sets in semi-honest model has...Efficiency and scalability are still the bottleneck for secure multi-party computation geometry （SMCG）. In this work a secure planar convex hull （SPCH） protocol for large-scaled point sets in semi-honest model has been proposed efficiently to solve the above problems. Firstly, a novel priva- cy-preserving point-inclusion （PPPI） protocol is designed based on the classic homomorphic encryp- tion and secure cross product protocol, and it is demonstrated that the complexity of PPPI protocol is independent of the vertex size of the input convex hull. And then on the basis of the novel PPPI pro- tocol, an effective SPCH protocol is presented. Analysis shows that this SPCH protocol has a good performance for large-scaled point sets compared with previous solutions. Moreover, analysis finds that the complexity of our SPCH protocol relies on the size of the points on the outermost layer of the input point sets only.展开更多
This paper was motivated by the existing problems of Cloud Data storage in Imo State University, Nigeria such as outsourced data causing the loss of data and misuse of customer information by unauthorized users or hac...This paper was motivated by the existing problems of Cloud Data storage in Imo State University, Nigeria such as outsourced data causing the loss of data and misuse of customer information by unauthorized users or hackers, thereby making customer/client data visible and unprotected. Also, this led to enormous risk of the clients/customers due to defective equipment, bugs, faulty servers, and specious actions. The aim if this paper therefore is to analyze a secure model using Unicode Transformation Format (UTF) base 64 algorithms for storage of data in cloud securely. The methodology used was Object Orientated Hypermedia Analysis and Design Methodology (OOHADM) was adopted. Python was used to develop the security model;the role-based access control (RBAC) and multi-factor authentication (MFA) to enhance security Algorithm were integrated into the Information System developed with HTML 5, JavaScript, Cascading Style Sheet (CSS) version 3 and PHP7. This paper also discussed some of the following concepts;Development of Computing in Cloud, Characteristics of computing, Cloud deployment Model, Cloud Service Models, etc. The results showed that the proposed enhanced security model for information systems of cooperate platform handled multiple authorization and authentication menace, that only one login page will direct all login requests of the different modules to one Single Sign On Server (SSOS). This will in turn redirect users to their requested resources/module when authenticated, leveraging on the Geo-location integration for physical location validation. The emergence of this newly developed system will solve the shortcomings of the existing systems and reduce time and resources incurred while using the existing system.展开更多
文摘Federated Learning(FL)enables joint training over distributed devices without data exchange but is highly vulnerable to attacks by adversaries in the form of model poisoning and malicious update injection.This work proposes Secured-FL,a blockchain-based defensive framework that combines smart contract-based authentication,clustering-driven outlier elimination,and dynamic threshold adjustment to defend against adversarial attacks.The framework was implemented on a private Ethereum network with a Proof-of-Authority consensus algorithm to ensure tamper-resistant and auditable model updates.Large-scale simulation on the Cyber Data dataset,under up to 50%malicious client settings,demonstrates Secured-FL achieves 6%-12%higher accuracy,9%-15%lower latency,and approximately 14%less computational expense compared to the PPSS benchmark framework.Additional tests,including confusion matrices,ROC and Precision-Recall curves,and ablation tests,confirm the interpretability and robustness of the defense.Tests for scalability also show consistent performance up to 500 clients,affirming appropriateness to reasonably large deployments.These results make Secured-FL a feasible,adversarially resilient FL paradigm with promising potential for application in smart cities,medicine,and other mission-critical IoT deployments.
文摘Although Named Entity Recognition(NER)in cybersecurity has historically concentrated on threat intelligence,vital security data can be found in a variety of sources,such as open-source intelligence and unprocessed tool outputs.When dealing with technical language,the coexistence of structured and unstructured data poses serious issues for traditional BERT-based techniques.We introduce a three-phase approach for improved NER inmulti-source cybersecurity data that makes use of large language models(LLMs).To ensure thorough entity coverage,our method starts with an identification module that uses dynamic prompting techniques.To lessen hallucinations,the extraction module uses confidence-based self-assessment and cross-checking using regex validation.The tagging module links to knowledge bases for contextual validation and uses SecureBERT in conjunction with conditional random fields to detect entity boundaries precisely.Our framework creates efficient natural language segments by utilizing decoderbased LLMs with 10B parameters.When compared to baseline SecureBERT implementations,evaluation across four cybersecurity data sources shows notable gains,with a 9.4%–25.21%greater recall and a 6.38%–17.3%better F1-score.Our refined model matches larger models and achieves 2.6%–4.9%better F1-score for technical phrase recognition than the state-of-the-art alternatives Claude 3.5 Sonnet,Llama3-8B,and Mixtral-7B.The three-stage architecture identification-extraction-tagging pipeline tackles important cybersecurity NER issues.Through effective architectures,these developments preserve deployability while setting a new standard for entity extraction in challenging security scenarios.The findings show how specific enhancements in hybrid recognition,validation procedures,and prompt engineering raise NER performance above monolithic LLM approaches in cybersecurity applications,especially for technical entity extraction fromheterogeneous sourceswhere conventional techniques fall short.Because of itsmodular nature,the framework can be upgraded at the component level as new methods are developed.
基金supported in part by the National Natural Science Foundation of China under Grants 62102450,62272478 and the Independent Research Project of a Certain Unit under Grant ZZKY20243127。
文摘Traditional steganography conceals information by modifying cover data,but steganalysis tools easily detect such alterations.While deep learning-based steganography often involves high training costs and complex deployment.Diffusion model-based methods face security vulnerabilities,particularly due to potential information leakage during generation.We propose a fixed neural network image steganography framework based on secure diffu-sion models to address these challenges.Unlike conventional approaches,our method minimizes cover modifications through neural network optimization,achieving superior steganographic performance in human visual perception and computer vision analyses.The cover images are generated in an anime style using state-of-the-art diffusion models,ensuring the transmitted images appear more natural.This study introduces fixed neural network technology that allows senders to transmit only minimal critical information alongside stego-images.Recipients can accurately reconstruct secret images using this compact data,significantly reducing transmission overhead compared to conventional deep steganography.Furthermore,our framework innovatively integrates ElGamal,a cryptographic algorithm,to protect critical information during transmission,enhancing overall system security and ensuring end-to-end information protection.This dual optimization of payload reduction and cryptographic reinforcement establishes a new paradigm for secure and efficient image steganography.
基金National Natural Science Foundation of China(Nos.42301473,42271424,42171397)Chinese Postdoctoral Innovation Talents Support Program(No.BX20230299)+2 种基金China Postdoctoral Science Foundation(No.2023M742884)Natural Science Foundation of Sichuan Province(Nos.24NSFSC2264,2025ZNSFSC0322)Key Research and Development Project of Sichuan Province(No.24ZDYF0633).
文摘As a key node of modern transportation network,the informationization management of road tunnels is crucial to ensure the operation safety and traffic efficiency.However,the existing tunnel vehicle modeling methods generally have problems such as insufficient 3D scene description capability and low dynamic update efficiency,which are difficult to meet the demand of real-time accurate management.For this reason,this paper proposes a vehicle twin modeling method for road tunnels.This approach starts from the actual management needs,and supports multi-level dynamic modeling from vehicle type,size to color by constructing a vehicle model library that can be flexibly invoked;at the same time,semantic constraint rules with geometric layout,behavioral attributes,and spatial relationships are designed to ensure that the virtual model matches with the real model with a high degree of similarity;ultimately,the prototype system is constructed and the case region is selected for the case study,and the dynamic vehicle status in the tunnel is realized by integrating real-time monitoring data with semantic constraints for precise virtual-real mapping.Finally,the prototype system is constructed and case experiments are conducted in selected case areas,which are combined with real-time monitoring data to realize dynamic updating and three-dimensional visualization of vehicle states in tunnels.The experiments show that the proposed method can run smoothly with an average rendering efficiency of 17.70 ms while guaranteeing the modeling accuracy(composite similarity of 0.867),which significantly improves the real-time and intuitive tunnel management.The research results provide reliable technical support for intelligent operation and emergency response of road tunnels,and offer new ideas for digital twin modeling of complex scenes.
文摘Software security poses substantial risks to our society because software has become part of our life. Numerous techniques have been proposed to resolve or mitigate the impact of software security issues. Among them, software testing and analysis are two of the critical methods, which significantly benefit from the advancements in deep learning technologies. Due to the successful use of deep learning in software security, recently,researchers have explored the potential of using large language models(LLMs) in this area. In this paper, we systematically review the results focusing on LLMs in software security. We analyze the topics of fuzzing, unit test, program repair, bug reproduction, data-driven bug detection, and bug triage. We deconstruct these techniques into several stages and analyze how LLMs can be used in the stages. We also discuss the future directions of using LLMs in software security, including the future directions for the existing use of LLMs and extensions from conventional deep learning research.
文摘ChatGPT is a powerful artificial intelligence(AI)language model that has demonstrated significant improvements in various natural language processing(NLP) tasks. However, like any technology, it presents potential security risks that need to be carefully evaluated and addressed. In this survey, we provide an overview of the current state of research on security of using ChatGPT, with aspects of bias, disinformation, ethics, misuse,attacks and privacy. We review and discuss the literature on these topics and highlight open research questions and future directions.Through this survey, we aim to contribute to the academic discourse on AI security, enriching the understanding of potential risks and mitigations. We anticipate that this survey will be valuable for various stakeholders involved in AI development and usage, including AI researchers, developers, policy makers, and end-users.
基金supported by the National Key R&D Program of China under Grant No.2022YFB3103500the National Natural Science Foundation of China under Grants No.62402087 and No.62020106013+3 种基金the Sichuan Science and Technology Program under Grant No.2023ZYD0142the Chengdu Science and Technology Program under Grant No.2023-XT00-00002-GXthe Fundamental Research Funds for Chinese Central Universities under Grants No.ZYGX2020ZB027 and No.Y030232063003002the Postdoctoral Innovation Talents Support Program under Grant No.BX20230060.
文摘The integration of artificial intelligence(AI)technology,particularly large language models(LLMs),has become essential across various sectors due to their advanced language comprehension and generation capabilities.Despite their transformative impact in fields such as machine translation and intelligent dialogue systems,LLMs face significant challenges.These challenges include safety,security,and privacy concerns that undermine their trustworthiness and effectiveness,such as hallucinations,backdoor attacks,and privacy leakage.Previous works often conflated safety issues with security concerns.In contrast,our study provides clearer and more reasonable definitions for safety,security,and privacy within the context of LLMs.Building on these definitions,we provide a comprehensive overview of the vulnerabilities and defense mechanisms related to safety,security,and privacy in LLMs.Additionally,we explore the unique research challenges posed by LLMs and suggest potential avenues for future research,aiming to enhance the robustness and reliability of LLMs in the face of emerging threats.
文摘Traditional multi-level security(MLS)systems have the defect of centralizing authorized facilities,which is difficult to meet the security requirements of modern distributed peer-to-peer network architecture.Blockchain is widely used in the field of access control with its decentralization,traceability and non-defective modification.Combining the blockchain technology and the Bell-LaPadula model,we propose a new access control model,named BCBLPM,for MLS environment.The“multi-chain”blockchain architecture is used for dividing resources into isolated access domains,providing a fine-grained data protection mechanism.The access control policies are implemented by smart contracts deployed in each access domain,so that the side chains of different access domains storage access records from outside and maintain the integrity of the records.Finally,we implement the BC-BLPM prototype system using the Hyperledger Fabric.The experimental and analytical results show that the model can adapt well to the needs of multi-level security environment,and it has the feasibility of application in actual scenarios.
基金the National Natural Science Foundation of China (No.60970119)the National Basic Research Program (973) of China (No.2007CB311201)
文摘To give concurrent consideration both the efficiency and the security(intensity of intractable problem) in the standard model,a chosen ciphertext secure identity-based broadcast encryption is proposed.Against the chosen ciphertext security model,by using identity(ID) sequence and adding additional information in ciphertext,the self-adaptive chosen identity security(the full security) and the chosen ciphertext security are gained simultaneously.The reduction of scheme's security is the decisional bilinear Diffie-Hellman(BDH) intractable assumption,and the proof of security shows that the proposed scheme is indistinguishable against adaptive chosen ciphertext attacks in the standard model under the decisional BDH intractable assumption.So the security level is improved,and it is suitable for higher security environment.
基金supported by National Key Basic Research Program(973 Program) under Grant No.2011CB302903National Natural Science Foundation under Grant No.60873231+1 种基金Key Program of Natural Science for Universities of Jiangsu Province under Grant No.10KJA510035Scientific Research Foundation of NJUPT under Grant No.NY209016,China
文摘In view of the security weakness in resisting the active attacks by malicious nodes in mobile ad hoc networks,the trust metric is introduced to defend those attacks by loading a trust model on the previously proposed Distance-Based LAR.The improved Secure Trust-based Location-Aided Routing algorithm utilizes direct trust and recommendation trust to prevent malicious nodes with low trust values from joining the forwarding.Simulation results reveal that ST-LAR can resist attacks by malicious nodes effectively;furthermore,it also achieves better performance than DBLAR in terms of average end-to-end delay,packet delivery success ratio and throughput.
文摘Recently,the 2025 Central Conference on Work Related to Neighboring Countries was held in Beijing.As an important theoretical innovation,the conference emphasized for the first time pursuing“the model of security for Asia that features sharing weal and woe,seeking common ground while shelving differences,and prioritizing dialogue and consultation.”1 This fully demonstrates that China prioritizes neighborhood on its diplomatic agenda,regards security and stability in its neighborhood as a core strategic support,and is ready to collaborate with neighboring countries for a future of shared peace,development,and prosperity.
基金The Fundamental Research Funds for the Central Universities(No.2242022k60005)Purple Mountain Laboratories for Network and Communication Security,and National Science Foundation(No.62233003).
文摘In response to the current gaps in ef-fective proactive defense methods within applica-tion security and the limited integration of security components with applications,this paper proposes a biomimetic security model,called NeuroShield,specifically designed for web applications.Inspired by the“perception-strategy-effect-feedback”mechanism of the human nervous control system,the model inte-grates biomimetic elements akin of neural receptors and effectors into applications.This integration fa-cilitates a multifaceted approach to security:enabling data introspection for detailed perception and regula-tion of application behavior,providing proactive de-fense capabilities to detect and block security risks in real-time,and incorporating feedback optimization to continuously adjust and enhance security strategies based on prevailing conditions.Experimental results affirm the efficacy of this neural control mechanism-based biomimetic security model,demonstrating a proactive defense success rate exceeding 95%,thereby offering a theoretical and structural foundation for biomimetic immunity in web applications.
文摘Security is the cor nerstone of a country's peace and stability and the prerequisite for its survival and development.All countries around the world regard security as their top priority.Since most Asian countries suffered from colonial aggression and plundering for a long time in history,they as a whole attach special importance to national security.
基金supported by the Deanship of Graduate Studies and Scientific Research at Qassim University via Grant No.(QU-APC-2025).
文摘The Internet of Things (IoT) and edge-assisted networking infrastructures are capable of bringing data processing and accessibility services locally at the respective edge rather than at a centralized module. These infrastructures are very effective in providing a fast response to the respective queries of the requesting modules, but their distributed nature has introduced other problems such as security and privacy. To address these problems, various security-assisted communication mechanisms have been developed to safeguard every active module, i.e., devices and edges, from every possible vulnerability in the IoT. However, these methodologies have neglected one of the critical issues, which is the prediction of fraudulent devices, i.e., adversaries, preferably as early as possible in the IoT. In this paper, a hybrid communication mechanism is presented where the Hidden Markov Model (HMM) predicts the legitimacy of the requesting device (both source and destination), and the Advanced Encryption Standard (AES) safeguards the reliability of the transmitted data over a shared communication medium, preferably through a secret shared key, i.e., , and timestamp information. A device becomes trusted if it has passed both evaluation levels, i.e., HMM and message decryption, within a stipulated time interval. The proposed hybrid, along with existing state-of-the-art approaches, has been simulated in the realistic environment of the IoT to verify the security measures. These evaluations were carried out in the presence of intruders capable of launching various attacks simultaneously, such as man-in-the-middle, device impersonations, and masquerading attacks. Moreover, the proposed approach has been proven to be more effective than existing state-of-the-art approaches due to its exceptional performance in communication, processing, and storage overheads, i.e., 13%, 19%, and 16%, respectively. Finally, the proposed hybrid approach is pruned against well-known security attacks in the IoT.
文摘Processing police incident data in public security involves complex natural language processing(NLP)tasks,including information extraction.This data contains extensive entity information—such as people,locations,and events—while also involving reasoning tasks like personnel classification,relationship judgment,and implicit inference.Moreover,utilizing models for extracting information from police incident data poses a significant challenge—data scarcity,which limits the effectiveness of traditional rule-based and machine-learning methods.To address these,we propose TIPS.In collaboration with public security experts,we used de-identified police incident data to create templates that enable large language models(LLMs)to populate data slots and generate simulated data,enhancing data density and diversity.We then designed schemas to efficiently manage complex extraction and reasoning tasks,constructing a high-quality dataset and fine-tuning multiple open-source LLMs.Experiments showed that the fine-tuned ChatGLM-4-9B model achieved an F1 score of 87.14%,nearly 30%higher than the base model,significantly reducing error rates.Manual corrections further improved performance by 9.39%.This study demonstrates that combining largescale pre-trained models with limited high-quality domain-specific data can greatly enhance information extraction in low-resource environments,offering a new approach for intelligent public security applications.
文摘Large models,such as large language models(LLMs),vision-language models(VLMs),and multimodal agents,have become key elements in artificial intelli⁃gence(AI)systems.Their rapid development has greatly improved perception,generation,and decision-making in various fields.However,their vast scale and complexity bring about new security challenges.Issues such as backdoor vulnerabilities during training,jailbreaking in multimodal rea⁃soning,and data provenance and copyright auditing have made security a critical focus for both academia and industry.
文摘A multilevel secure relation hierarchical data model for multilevel secure database is extended from the relation hierarchical data model in single level environment in this paper. Based on the model, an upper lower layer relationalintegrity is presented after we analyze and eliminate the covert channels caused by the database integrity.Two SQL statements are extended to process polyinstantiation in the multilevel secure environment.The system based on the multilevel secure relation hierarchical data model is capable of integratively storing and manipulating complicated objects ( e.g. , multilevel spatial data) and conventional data ( e.g. , integer, real number and character string) in multilevel secure database.
基金this project under Geran Putra Inisiatif(GPI)with reference of GP-GPI/2023/976210。
文摘Accurate time synchronization is fundamental to the correct and efficient operation of Wireless Sensor Networks(WSNs),especially in security-critical,time-sensitive applications.However,most existing protocols degrade substantially under malicious interference.We introduce iSTSP,an Intelligent and Secure Time Synchronization Protocol that implements a four-stage defense pipeline to ensure robust,precise synchronization even in hostile environments:(1)trust preprocessing that filters node participation using behavioral trust scoring;(2)anomaly isolation employing a lightweight autoencoder to detect and excise malicious nodes in real time;(3)reliability-weighted consensus that prioritizes high-trust nodes during time aggregation;and(4)convergence-optimized synchronization that dynamically adjusts parameters using theoretical stability bounds.We provide rigorous convergence analysis including a closed-form expression for convergence time,and validate the protocol through both simulations and realworld experiments on a controlled 16-node testbed.Under Sybil attacks with five malicious nodes within this testbed,iSTSP maintains synchronization error increases under 12%and achieves a rapid convergence.Compared to state-ofthe-art protocols like TPSN,SE-FTSP,and MMAR-CTS,iSTSP offers 60%faster detection,broader threat coverage,and more than 7 times lower synchronization error,with a modest 9.3%energy overhead over 8 h.We argue this is an acceptable trade-off for mission-critical deployments requiring guaranteed security.These findings demonstrate iSTSP’s potential as a reliable solution for secure WSN synchronization and motivate future work on large-scale IoT deployments and integration with energy-efficient communication protocols.
基金Supported by the Young Scientists Program of CUEB(No.2014XJQ016,00791462722337)National Natural Science Foundation of China(No.61302087)+1 种基金Young Scientific Research Starting Foundation of CUEBImprove Scientific Research Foundation of Beijing Education
文摘Efficiency and scalability are still the bottleneck for secure multi-party computation geometry （SMCG）. In this work a secure planar convex hull （SPCH） protocol for large-scaled point sets in semi-honest model has been proposed efficiently to solve the above problems. Firstly, a novel priva- cy-preserving point-inclusion （PPPI） protocol is designed based on the classic homomorphic encryp- tion and secure cross product protocol, and it is demonstrated that the complexity of PPPI protocol is independent of the vertex size of the input convex hull. And then on the basis of the novel PPPI pro- tocol, an effective SPCH protocol is presented. Analysis shows that this SPCH protocol has a good performance for large-scaled point sets compared with previous solutions. Moreover, analysis finds that the complexity of our SPCH protocol relies on the size of the points on the outermost layer of the input point sets only.
文摘This paper was motivated by the existing problems of Cloud Data storage in Imo State University, Nigeria such as outsourced data causing the loss of data and misuse of customer information by unauthorized users or hackers, thereby making customer/client data visible and unprotected. Also, this led to enormous risk of the clients/customers due to defective equipment, bugs, faulty servers, and specious actions. The aim if this paper therefore is to analyze a secure model using Unicode Transformation Format (UTF) base 64 algorithms for storage of data in cloud securely. The methodology used was Object Orientated Hypermedia Analysis and Design Methodology (OOHADM) was adopted. Python was used to develop the security model;the role-based access control (RBAC) and multi-factor authentication (MFA) to enhance security Algorithm were integrated into the Information System developed with HTML 5, JavaScript, Cascading Style Sheet (CSS) version 3 and PHP7. This paper also discussed some of the following concepts;Development of Computing in Cloud, Characteristics of computing, Cloud deployment Model, Cloud Service Models, etc. The results showed that the proposed enhanced security model for information systems of cooperate platform handled multiple authorization and authentication menace, that only one login page will direct all login requests of the different modules to one Single Sign On Server (SSOS). This will in turn redirect users to their requested resources/module when authenticated, leveraging on the Geo-location integration for physical location validation. The emergence of this newly developed system will solve the shortcomings of the existing systems and reduce time and resources incurred while using the existing system.
