The global surge in Artificial Intelligence(AI)has been triggered by the impressive performance of deep-learning models based on the Transformer architecture.However,the efficacy of such models is increasingly depende...The global surge in Artificial Intelligence(AI)has been triggered by the impressive performance of deep-learning models based on the Transformer architecture.However,the efficacy of such models is increasingly dependent on the volume and quality of data.Data are often distributed across institutions and companies,making cross-organizational data transfer vulnerable to privacy breaches and subject to privacy laws and trade secret regulations.These privacy and security concerns continue to pose major challenges to collaborative training and inference in multi-source data environments.These challenges are particularly significant for Transformer models,where the complex internal encryption computations drastically reduce computational efficiency,ultimately threatening the model's practical applicability.We hence introduce Secformer,an innovative architecture specifically designed to protect the privacy of Transformer-like models.Secformer separates the encoder and decoder modules,enabling the decomposition of computation flows in Transformer-like models and their efficient mapping to Multi-Party Computation(MPC)protocols.This design effectively addresses privacy leakage issues during the collaborative computation process of Transformer models.To prevent performance degradation caused by encrypted attention modules,we propose a modular design strategy that optimizes high-level components by reconstructing low-level operators.We further analyze the security of Secformer's core components,presenting security definitions and formal proofs.We construct a library of fundamental operators and core modules using atomic-level component designs as the basic building blocks for encoders and decoders.Moreover,these components can serve as foundational operators for other Transformer-like models.Extensive experimental evaluations demonstrate Secformer's excellent performance while preserving privacy and offering universal adaptability for Transformer-like models.展开更多
With the rapid development of the Artificial Intelligence of Things(AIoT),convolutional neural networks(CNNs)have demonstrated potential and remarkable performance in AIoT applications due to their excellent performan...With the rapid development of the Artificial Intelligence of Things(AIoT),convolutional neural networks(CNNs)have demonstrated potential and remarkable performance in AIoT applications due to their excellent performance in various inference tasks.However,the users have concerns about privacy leakage for the use of AI and the performance and efficiency of computing on resource-constrained IoT edge devices.Therefore,this paper proposes an efficient privacy-preserving CNN framework(i.e.,EPPA)based on the Fully Homomorphic Encryption(FHE)scheme for AIoT application scenarios.In the plaintext domain,we verify schemes with different activation structures to determine the actual activation functions applicable to the corresponding ciphertext domain.Within the encryption domain,we integrate batch normalization(BN)into the convolutional layers to simplify the computation process.For nonlinear activation functions,we use composite polynomials for approximate calculation.Regarding the noise accumulation caused by homomorphic multiplication operations,we realize the refreshment of ciphertext noise through minimal“decryption-encryption”interactions,instead of adopting bootstrapping operations.Additionally,in practical implementation,we convert three-dimensional convolution into two-dimensional convolution to reduce the amount of computation in the encryption domain.Finally,we conduct extensive experiments on four IoT datasets,different CNN architectures,and two platforms with different resource configurations to evaluate the performance of EPPA in detail.展开更多
Large LanguageModels(LLMs)are increasingly utilized for semantic understanding and reasoning,yet their use in sensitive settings is limited by privacy concerns.This paper presents In-Mig,a mobile-agent architecture th...Large LanguageModels(LLMs)are increasingly utilized for semantic understanding and reasoning,yet their use in sensitive settings is limited by privacy concerns.This paper presents In-Mig,a mobile-agent architecture that integrates LLM reasoning within agents that can migrate across organizational venues.Unlike centralized approaches,In-Mig performs reasoning in situ,ensuring that raw data remains within institutional boundaries while allowing for cross-venue synthesis.The architecture features a policy-scoped memory model,utility-driven route planning,and cryptographic trust enforcement.Aprototype using JADE for mobility and quantizedMistral-7B demonstrates practical feasibility.Evaluation across various scenarios shows that In-Mig achieves 92%similarity to centralized baselines,confirming its utility and strong privacy guarantees.These results suggest that migrating,privacy-preserving LLM agents can effectively support decentralized reasoning in trust-sensitive domains.展开更多
In the competitive retail industry of the digital era,data-driven insights into gender-specific customer behavior are essential.They support the optimization of store performance,layout design,product placement,and ta...In the competitive retail industry of the digital era,data-driven insights into gender-specific customer behavior are essential.They support the optimization of store performance,layout design,product placement,and targeted marketing.However,existing computer vision solutions often rely on facial recognition to gather such insights,raising significant privacy and ethical concerns.To address these issues,this paper presents a privacypreserving customer analytics system through two key strategies.First,we deploy a deep learning framework using YOLOv9s,trained on the RCA-TVGender dataset.Cameras are positioned perpendicular to observation areas to reduce facial visibility while maintaining accurate gender classification.Second,we apply AES-128 encryption to customer position data,ensuring secure access and regulatory compliance.Our system achieved overall performance,with 81.5%mAP@50,77.7%precision,and 75.7%recall.Moreover,a 90-min observational study confirmed the system’s ability to generate privacy-protected heatmaps revealing distinct behavioral patterns between male and female customers.For instance,women spent more time in certain areas and showed interest in different products.These results confirm the system’s effectiveness in enabling personalized layout and marketing strategies without compromising privacy.展开更多
Background:Mastitis seriously affects the mammary health of humans and animals.Studies have found that inflammation and oxidative stress play key roles in the occur-rence and development of mastitis.Therefore,in-depth...Background:Mastitis seriously affects the mammary health of humans and animals.Studies have found that inflammation and oxidative stress play key roles in the occur-rence and development of mastitis.Therefore,in-depth research on related molecular mechanisms is of great significance.Methods:Postpartum mice were anesthetized with pentobarbital and administered lipopolysaccharide to develop the mouse mastitis model.Proteomic analysis was per-formed to compare protein expression in mitochondria-associated endoplasmic retic-ulum membranes(MAM)from two mouse mammary gland groups.Western blot was used to detect the expression of MAM-related proteins in mitochondria.AlphaFold3 was used to predict the molecular structures of phosphofurin acidic cluster sorting protein 2(PACS2)and mitofusin 2(MFN2)and their interaction levels.The MFN2-PACS2 interaction was investigated using co-immunoprecipitation and small interfer-ing RNA.Results:The results showed that the inflammation level in the mammary gland tissue of mice with mastitis significantly increased,the total antioxidant capacity decreased,and the expression of MAM-related proteins MFN2 and PACS2 was significantly downregulated.In cell experiments,overexpression of MFN2 can inhibit inflamma-tion and oxidative stress responses,and promote the interaction between MFN2 and PACS2 to affect the formation of MAMs.Conclusion:In summary,this study suggests that mastitis can alter the expression of MAM-related proteins in mouse breast tissue.The interaction between MFN2 and PACS2 regulates the formation of MAMs.Overexpression of MFN2 can promote the formation of MAMs and inhibit inflammation and oxidative stress response in mam-mary epithelial cells.Our results provided a new theoretical basis and potential thera-peutic targets for the prevention and treatment of mastitis.展开更多
As the demand for cross-departmental data collaboration continues to grow,traditional encryption methods struggle to balance data privacy with computational efficiency.This paper proposes a cross-departmental privacy-...As the demand for cross-departmental data collaboration continues to grow,traditional encryption methods struggle to balance data privacy with computational efficiency.This paper proposes a cross-departmental privacy-preserving computation framework based on BFV homomorphic encryption,threshold decryption,and blockchain technology.The proposed scheme leverages homomorphic encryption to enable secure computations between sales,finance,and taxation departments,ensuring that sensitive data remains encrypted throughout the entire process.A threshold decryption mechanism is employed to prevent single-point data leakage,while blockchain and IPFS are integrated to ensure verifiability and tamper-proof storage of computation results.Experimental results demonstrate that with 5,000 sample data entries,the framework performs efficiently and is highly scalable in key stages such as sales encryption,cost calculation,and tax assessment,thereby validating its practical feasibility and security.展开更多
Federated learning(FL)is a distributed machine learning paradigm that excels at preserving data privacy when using data from multiple parties.When combined with Fog Computing,FL offers enhanced capabilities for machin...Federated learning(FL)is a distributed machine learning paradigm that excels at preserving data privacy when using data from multiple parties.When combined with Fog Computing,FL offers enhanced capabilities for machine learning applications in the Internet of Things(IoT).However,implementing FL across large-scale distributed fog networks presents significant challenges in maintaining privacy,preventing collusion attacks,and ensuring robust data aggregation.To address these challenges,we propose an Efficient Privacy-preserving and Robust Federated Learning(EPRFL)scheme for fog computing scenarios.Specifically,we first propose an efficient secure aggregation strategy based on the improved threshold homomorphic encryption algorithm,which is not only resistant to model inference and collusion attacks,but also robust to fog node dropping.Then,we design a dynamic gradient filtering method based on cosine similarity to further reduce the communication overhead.To minimize training delays,we develop a dynamic task scheduling strategy based on comprehensive score.Theoretical analysis demonstrates that EPRFL offers robust security and low latency.Extensive experimental results indicate that EPRFL outperforms similar strategies in terms of privacy preserving,model performance,and resource efficiency.展开更多
The rapid proliferation of Internet of Things(IoT)devices has heightened security concerns,making intrusion detection a pivotal challenge in safeguarding these networks.Traditional centralized Intrusion Detection Syst...The rapid proliferation of Internet of Things(IoT)devices has heightened security concerns,making intrusion detection a pivotal challenge in safeguarding these networks.Traditional centralized Intrusion Detection Systems(IDS)often fail to meet the privacy requirements and scalability demands of large-scale IoT ecosystems.To address these challenges,we propose an innovative privacy-preserving approach leveraging Federated Learning(FL)for distributed intrusion detection.Our model eliminates the need for aggregating sensitive data on a central server by training locally on IoT devices and sharing only encrypted model updates,ensuring enhanced privacy and scalability without compromising detection accuracy.Key innovations of this research include the integration of advanced deep learning techniques for real-time threat detection with minimal latency and a novel model to fortify the system’s resilience against diverse cyber-attacks such as Distributed Denial of Service(DDoS)and malware injections.Our evaluation on three benchmark IoT datasets demonstrates significant improvements:achieving 92.78%accuracy on NSL-KDD,91.47%on BoT-IoT,and 92.05%on UNSW-NB15.The precision,recall,and F1-scores for all datasets consistently exceed 91%.Furthermore,the communication overhead was reduced to 85 MB for NSL-KDD,105 MB for BoT-IoT,and 95 MB for UNSW-NB15—substantially lower than traditional centralized IDS approaches.This study contributes to the domain by presenting a scalable,secure,and privacy-preserving solution tailored to the unique characteristics of IoT environments.The proposed framework is adaptable to dynamic and heterogeneous settings,with potential applications extending to other privacy-sensitive domains.Future work will focus on enhancing the system’s efficiency and addressing emerging challenges such as model poisoning attacks in federated environments.展开更多
Privacy-Preserving Computation(PPC)comprises the techniques,schemes and protocols which ensure privacy and confidentiality in the context of secure computation and data analysis.Most of the current PPC techniques rely...Privacy-Preserving Computation(PPC)comprises the techniques,schemes and protocols which ensure privacy and confidentiality in the context of secure computation and data analysis.Most of the current PPC techniques rely on the complexity of cryptographic operations,which are expected to be efficiently solved by quantum computers soon.This review explores how PPC can be built on top of quantum computing itself to alleviate these future threats.We analyze quantum proposals for Secure Multi-party Computation,Oblivious Transfer and Homomorphic Encryption from the last decade focusing on their maturity and the challenges they currently face.Our findings show a strong focus on purely theoretical works,but a rise on the experimental consideration of these techniques in the last 5 years.The applicability of these techniques to actual use cases is an underexplored aspect which could lead to the practical assessment of these techniques.展开更多
Federated Learning(FL)has emerged as a promising distributed machine learning paradigm that enables multi-party collaborative training while eliminating the need for raw data sharing.However,its reliance on a server i...Federated Learning(FL)has emerged as a promising distributed machine learning paradigm that enables multi-party collaborative training while eliminating the need for raw data sharing.However,its reliance on a server introduces critical security vulnerabilities:malicious servers can infer private information from received local model updates or deliberately manipulate aggregation results.Consequently,achieving verifiable aggregation without compromising client privacy remains a critical challenge.To address these problem,we propose a reversible data hiding in encrypted domains(RDHED)scheme,which designs joint secret message embedding and extraction mechanism.This approach enables clients to embed secret messages into ciphertext redundancy spaces generated during model encryption.During the server aggregation process,the embedded messages from all clients fuse within the ciphertext space to form a joint embedding message.Subsequently,clients can decrypt the aggregated results and extract this joint embedding message for verification purposes.Building upon this foundation,we integrate the proposed RDHED scheme with linear homomorphic hash and digital signatures to design a verifiable privacy-preserving aggregation protocol for single-server architectures(VPAFL).Theoretical proofs and experimental analyses show that VPAFL can effectively protect user privacy,achieve lightweight computational and communication overhead of users for verification,and present significant advantages with increasing model dimension.展开更多
The progress of modern industry has given rise to great requirements for network transmission latency and reliability in domains such as smart grid and intelligent driving.To address these challenges,the concept of Ti...The progress of modern industry has given rise to great requirements for network transmission latency and reliability in domains such as smart grid and intelligent driving.To address these challenges,the concept of Time-sensitive networking(TSN)is proposed by IEEE 802.1TSN working group.In order to achieve low latency,Cyclic queuing and forwarding(CQF)mechanism is introduced to schedule Timetriggered(TT)flows.In this paper,we construct a TSN model based on CQF and formulate the flow scheduling problem as an optimization problem aimed at maximizing the success rate of flow scheduling.The problem is tackled by a novel algorithm that makes full use of the characteristics and the relationship between the flows.Firstly,by K-means algorithm,the flows are initially partitioned into subsets based on their correlations.Subsequently,the flows within each subset are sorted by a new special criteria extracted from multiple features of flow.Finally,a flow offset selecting method based on load balance is used for resource mapping,so as to complete the process of flow scheduling.Experimental results demonstrate that the proposed algorithm exhibits significant advantages in terms of scheduling success rate and time efficiency.展开更多
The somatotopic representation of specific body parts is a well-established spatial organizational principle in the primary somatosensory and motor cortices.
The main function of electronic support measure system is to detect threating signals in order to take countermeasures against them. To accomplish this objective, a process of associating each interleaved pulse with i...The main function of electronic support measure system is to detect threating signals in order to take countermeasures against them. To accomplish this objective, a process of associating each interleaved pulse with its emitter must be done. This process is termed sorting or de-interleaving. A novel point symmetry based radar sorting (PSBRS) algorithm is addressed. In order to deal with all kinds of radar signals, the symmetry measure distance is used to cluster pulses instead of the conventional Euclidean distance. The reference points of the symmetrical clusters are initialized by the alternative fuzzy c-means (AFCM) algorithm to ameliorate the effects of noise and the false sorting. Besides, the density filtering (DF) algorithm is proposed to discard the noise pulses or clutter. The performance of the algorithm is evaluated under the effects of noise and missing pulses. It has been observed that the PSBRS algorithm can cope with a large number of noise pulses and it is completely independent of missing pulses. Finally, PSBRS is compared with some benchmark algorithms, and the simulation results reveal the feasibility and efficiency of the algorithm.展开更多
The non-dominated sorting genetic algorithm （NSGA） is improved with the controlled elitism and dynamic crowding distance. A novel multi-objective optimization algorithm is obtained for wind turbine blades. As an exa...The non-dominated sorting genetic algorithm （NSGA） is improved with the controlled elitism and dynamic crowding distance. A novel multi-objective optimization algorithm is obtained for wind turbine blades. As an example, a 5 MW wind turbine blade design is presented by taking the maximum power coefficient and the minimum blade mass as the optimization objectives. The optimal results show that this algorithm has good performance in handling the multi-objective optimization of wind turbines, and it gives a Pareto-optimal solution set rather than the optimum solutions to the conventional multi objective optimization problems. The wind turbine blade optimization method presented in this paper provides a new and general algorithm for the multi-objective optimization of wind turbines.展开更多
Under the background of increasingly scarce ore worldwide and increasingly fierce market competition,developing the mining industry could be strongly restricted.Intelligent ore sorting equipment not only improves ore ...Under the background of increasingly scarce ore worldwide and increasingly fierce market competition,developing the mining industry could be strongly restricted.Intelligent ore sorting equipment not only improves ore use and enhances the economic benefits of enterprises but also increases the ore grade and lessens the grinding cost and tailings production.However,long-term research on intelligent ore sorting equipment found that the factors affecting sorting efficiency mainly include ore information identification technology,equipment sorting actuator,and information processing algorithm.The high precision,strong anti-interference capability,and high speed of these factors guarantee the separation efficiency of intelligent ore sorting equipment.Color ore sorter,X-ray ore transmission sorter,dual-energy X-ray transmission ore sorter,X-ray fluorescence ore sorter,and near-infrared ore sorter have been successfully developed in accordance with the different characteristics of minerals while ensuring the accuracy of equipment sorting and improving the equipment sorting efficiency.With the continuous improvement of mine automation level,the application of online element rapid analysis technology with high speed,high precision,and strong anti-interference capability in intelligent ore sorting equipment will become an inevitable trend of equipment development in the future.Laser-induced breakdown spectroscopy,transientγneutron activation analysis,online Fourier transform infrared spectroscopy,and nuclear magnetic resonance techniques will promote the development of ore sorting equipment.In addition,the improvement and joint application of additional high-speed and high-precision operation algorithms(such as peak area,principal component analysis,artificial neural network,partial least squares,and Monte Carlo library least squares methods)are an essential part of the development of intelligent ore sorting equipment in the future.展开更多
A novel class of periodically changing features hidden in radar pulse sequence environment,named G features,is proposed.Combining fractal theory and Hilbert-Huang transform,the features are extracted using changing ch...A novel class of periodically changing features hidden in radar pulse sequence environment,named G features,is proposed.Combining fractal theory and Hilbert-Huang transform,the features are extracted using changing characteristics of pulse parameters in radar emitter signals.The features can be applied in modern complex electronic warfare environment to address the issue of signal sorting when radar emitter pulse signal parameters severely or even completely overlap.Experiment results show that the proposed feature class and feature extraction method can discriminate periodically changing pulse sequence signal sorting features from radar pulse signal flow with complex variant features,therefore provide a new methodology for signal sorting.展开更多
基金supported by the National Natural Science Foundation of China under Grant 62471205in part by the Yunnan Fundamental Research Projects under Grant 202301AV070003in part by the Major Science and Technology Projects in Yunnan Province under Grant 202302AG050009。
文摘The global surge in Artificial Intelligence(AI)has been triggered by the impressive performance of deep-learning models based on the Transformer architecture.However,the efficacy of such models is increasingly dependent on the volume and quality of data.Data are often distributed across institutions and companies,making cross-organizational data transfer vulnerable to privacy breaches and subject to privacy laws and trade secret regulations.These privacy and security concerns continue to pose major challenges to collaborative training and inference in multi-source data environments.These challenges are particularly significant for Transformer models,where the complex internal encryption computations drastically reduce computational efficiency,ultimately threatening the model's practical applicability.We hence introduce Secformer,an innovative architecture specifically designed to protect the privacy of Transformer-like models.Secformer separates the encoder and decoder modules,enabling the decomposition of computation flows in Transformer-like models and their efficient mapping to Multi-Party Computation(MPC)protocols.This design effectively addresses privacy leakage issues during the collaborative computation process of Transformer models.To prevent performance degradation caused by encrypted attention modules,we propose a modular design strategy that optimizes high-level components by reconstructing low-level operators.We further analyze the security of Secformer's core components,presenting security definitions and formal proofs.We construct a library of fundamental operators and core modules using atomic-level component designs as the basic building blocks for encoders and decoders.Moreover,these components can serve as foundational operators for other Transformer-like models.Extensive experimental evaluations demonstrate Secformer's excellent performance while preserving privacy and offering universal adaptability for Transformer-like models.
基金supported by the Natural Science Foundation of China No.62362008the Major Scientific and Technological Special Project of Guizhou Province([2024]014).
文摘With the rapid development of the Artificial Intelligence of Things(AIoT),convolutional neural networks(CNNs)have demonstrated potential and remarkable performance in AIoT applications due to their excellent performance in various inference tasks.However,the users have concerns about privacy leakage for the use of AI and the performance and efficiency of computing on resource-constrained IoT edge devices.Therefore,this paper proposes an efficient privacy-preserving CNN framework(i.e.,EPPA)based on the Fully Homomorphic Encryption(FHE)scheme for AIoT application scenarios.In the plaintext domain,we verify schemes with different activation structures to determine the actual activation functions applicable to the corresponding ciphertext domain.Within the encryption domain,we integrate batch normalization(BN)into the convolutional layers to simplify the computation process.For nonlinear activation functions,we use composite polynomials for approximate calculation.Regarding the noise accumulation caused by homomorphic multiplication operations,we realize the refreshment of ciphertext noise through minimal“decryption-encryption”interactions,instead of adopting bootstrapping operations.Additionally,in practical implementation,we convert three-dimensional convolution into two-dimensional convolution to reduce the amount of computation in the encryption domain.Finally,we conduct extensive experiments on four IoT datasets,different CNN architectures,and two platforms with different resource configurations to evaluate the performance of EPPA in detail.
文摘Large LanguageModels(LLMs)are increasingly utilized for semantic understanding and reasoning,yet their use in sensitive settings is limited by privacy concerns.This paper presents In-Mig,a mobile-agent architecture that integrates LLM reasoning within agents that can migrate across organizational venues.Unlike centralized approaches,In-Mig performs reasoning in situ,ensuring that raw data remains within institutional boundaries while allowing for cross-venue synthesis.The architecture features a policy-scoped memory model,utility-driven route planning,and cryptographic trust enforcement.Aprototype using JADE for mobility and quantizedMistral-7B demonstrates practical feasibility.Evaluation across various scenarios shows that In-Mig achieves 92%similarity to centralized baselines,confirming its utility and strong privacy guarantees.These results suggest that migrating,privacy-preserving LLM agents can effectively support decentralized reasoning in trust-sensitive domains.
文摘In the competitive retail industry of the digital era,data-driven insights into gender-specific customer behavior are essential.They support the optimization of store performance,layout design,product placement,and targeted marketing.However,existing computer vision solutions often rely on facial recognition to gather such insights,raising significant privacy and ethical concerns.To address these issues,this paper presents a privacypreserving customer analytics system through two key strategies.First,we deploy a deep learning framework using YOLOv9s,trained on the RCA-TVGender dataset.Cameras are positioned perpendicular to observation areas to reduce facial visibility while maintaining accurate gender classification.Second,we apply AES-128 encryption to customer position data,ensuring secure access and regulatory compliance.Our system achieved overall performance,with 81.5%mAP@50,77.7%precision,and 75.7%recall.Moreover,a 90-min observational study confirmed the system’s ability to generate privacy-protected heatmaps revealing distinct behavioral patterns between male and female customers.For instance,women spent more time in certain areas and showed interest in different products.These results confirm the system’s effectiveness in enabling personalized layout and marketing strategies without compromising privacy.
基金National Natural Science Foundation of China,Grant/Award Number:32302826 and 32372961Jilin Provincial Special Project for Health Research Talents,Grant/Award Number:2020SCZ40China Postdoctoral Science Foundation,Grant/Award Number:2023M740623。
文摘Background:Mastitis seriously affects the mammary health of humans and animals.Studies have found that inflammation and oxidative stress play key roles in the occur-rence and development of mastitis.Therefore,in-depth research on related molecular mechanisms is of great significance.Methods:Postpartum mice were anesthetized with pentobarbital and administered lipopolysaccharide to develop the mouse mastitis model.Proteomic analysis was per-formed to compare protein expression in mitochondria-associated endoplasmic retic-ulum membranes(MAM)from two mouse mammary gland groups.Western blot was used to detect the expression of MAM-related proteins in mitochondria.AlphaFold3 was used to predict the molecular structures of phosphofurin acidic cluster sorting protein 2(PACS2)and mitofusin 2(MFN2)and their interaction levels.The MFN2-PACS2 interaction was investigated using co-immunoprecipitation and small interfer-ing RNA.Results:The results showed that the inflammation level in the mammary gland tissue of mice with mastitis significantly increased,the total antioxidant capacity decreased,and the expression of MAM-related proteins MFN2 and PACS2 was significantly downregulated.In cell experiments,overexpression of MFN2 can inhibit inflamma-tion and oxidative stress responses,and promote the interaction between MFN2 and PACS2 to affect the formation of MAMs.Conclusion:In summary,this study suggests that mastitis can alter the expression of MAM-related proteins in mouse breast tissue.The interaction between MFN2 and PACS2 regulates the formation of MAMs.Overexpression of MFN2 can promote the formation of MAMs and inhibit inflammation and oxidative stress response in mam-mary epithelial cells.Our results provided a new theoretical basis and potential thera-peutic targets for the prevention and treatment of mastitis.
文摘As the demand for cross-departmental data collaboration continues to grow,traditional encryption methods struggle to balance data privacy with computational efficiency.This paper proposes a cross-departmental privacy-preserving computation framework based on BFV homomorphic encryption,threshold decryption,and blockchain technology.The proposed scheme leverages homomorphic encryption to enable secure computations between sales,finance,and taxation departments,ensuring that sensitive data remains encrypted throughout the entire process.A threshold decryption mechanism is employed to prevent single-point data leakage,while blockchain and IPFS are integrated to ensure verifiability and tamper-proof storage of computation results.Experimental results demonstrate that with 5,000 sample data entries,the framework performs efficiently and is highly scalable in key stages such as sales encryption,cost calculation,and tax assessment,thereby validating its practical feasibility and security.
基金supported in part by the National Natural Science Foundation of China(62462053)the Science and Technology Foundation of Qinghai Province(2023-ZJ-731)+1 种基金the Open Project of the Qinghai Provincial Key Laboratory of Restoration Ecology in Cold Area(2023-KF-12)the Open Research Fund of Guangdong Key Laboratory of Blockchain Security,Guangzhou University。
文摘Federated learning(FL)is a distributed machine learning paradigm that excels at preserving data privacy when using data from multiple parties.When combined with Fog Computing,FL offers enhanced capabilities for machine learning applications in the Internet of Things(IoT).However,implementing FL across large-scale distributed fog networks presents significant challenges in maintaining privacy,preventing collusion attacks,and ensuring robust data aggregation.To address these challenges,we propose an Efficient Privacy-preserving and Robust Federated Learning(EPRFL)scheme for fog computing scenarios.Specifically,we first propose an efficient secure aggregation strategy based on the improved threshold homomorphic encryption algorithm,which is not only resistant to model inference and collusion attacks,but also robust to fog node dropping.Then,we design a dynamic gradient filtering method based on cosine similarity to further reduce the communication overhead.To minimize training delays,we develop a dynamic task scheduling strategy based on comprehensive score.Theoretical analysis demonstrates that EPRFL offers robust security and low latency.Extensive experimental results indicate that EPRFL outperforms similar strategies in terms of privacy preserving,model performance,and resource efficiency.
基金supported and funded by the Deanship of Graduate Studies and Scientific Research at Qassim University for financial support(QU-APC-2025).
文摘The rapid proliferation of Internet of Things(IoT)devices has heightened security concerns,making intrusion detection a pivotal challenge in safeguarding these networks.Traditional centralized Intrusion Detection Systems(IDS)often fail to meet the privacy requirements and scalability demands of large-scale IoT ecosystems.To address these challenges,we propose an innovative privacy-preserving approach leveraging Federated Learning(FL)for distributed intrusion detection.Our model eliminates the need for aggregating sensitive data on a central server by training locally on IoT devices and sharing only encrypted model updates,ensuring enhanced privacy and scalability without compromising detection accuracy.Key innovations of this research include the integration of advanced deep learning techniques for real-time threat detection with minimal latency and a novel model to fortify the system’s resilience against diverse cyber-attacks such as Distributed Denial of Service(DDoS)and malware injections.Our evaluation on three benchmark IoT datasets demonstrates significant improvements:achieving 92.78%accuracy on NSL-KDD,91.47%on BoT-IoT,and 92.05%on UNSW-NB15.The precision,recall,and F1-scores for all datasets consistently exceed 91%.Furthermore,the communication overhead was reduced to 85 MB for NSL-KDD,105 MB for BoT-IoT,and 95 MB for UNSW-NB15—substantially lower than traditional centralized IDS approaches.This study contributes to the domain by presenting a scalable,secure,and privacy-preserving solution tailored to the unique characteristics of IoT environments.The proposed framework is adaptable to dynamic and heterogeneous settings,with potential applications extending to other privacy-sensitive domains.Future work will focus on enhancing the system’s efficiency and addressing emerging challenges such as model poisoning attacks in federated environments.
基金supported by the Basque Government through the ELKARTEK program for Research and Innovation,under the BRTAQUANTUM project(Grant Agreement No.KK-2022/00041)。
文摘Privacy-Preserving Computation(PPC)comprises the techniques,schemes and protocols which ensure privacy and confidentiality in the context of secure computation and data analysis.Most of the current PPC techniques rely on the complexity of cryptographic operations,which are expected to be efficiently solved by quantum computers soon.This review explores how PPC can be built on top of quantum computing itself to alleviate these future threats.We analyze quantum proposals for Secure Multi-party Computation,Oblivious Transfer and Homomorphic Encryption from the last decade focusing on their maturity and the challenges they currently face.Our findings show a strong focus on purely theoretical works,but a rise on the experimental consideration of these techniques in the last 5 years.The applicability of these techniques to actual use cases is an underexplored aspect which could lead to the practical assessment of these techniques.
基金supported in part by the National Natural Science Foundation of China under Grants 62102450,62272478the Independent Research Project of a Certain Unit under Grant ZZKY20243127.
文摘Federated Learning(FL)has emerged as a promising distributed machine learning paradigm that enables multi-party collaborative training while eliminating the need for raw data sharing.However,its reliance on a server introduces critical security vulnerabilities:malicious servers can infer private information from received local model updates or deliberately manipulate aggregation results.Consequently,achieving verifiable aggregation without compromising client privacy remains a critical challenge.To address these problem,we propose a reversible data hiding in encrypted domains(RDHED)scheme,which designs joint secret message embedding and extraction mechanism.This approach enables clients to embed secret messages into ciphertext redundancy spaces generated during model encryption.During the server aggregation process,the embedded messages from all clients fuse within the ciphertext space to form a joint embedding message.Subsequently,clients can decrypt the aggregated results and extract this joint embedding message for verification purposes.Building upon this foundation,we integrate the proposed RDHED scheme with linear homomorphic hash and digital signatures to design a verifiable privacy-preserving aggregation protocol for single-server architectures(VPAFL).Theoretical proofs and experimental analyses show that VPAFL can effectively protect user privacy,achieve lightweight computational and communication overhead of users for verification,and present significant advantages with increasing model dimension.
基金supported by Science and Technology Project of State Grid Corporation Headquarters under Grant 5108-202218280A-2-170-XG(Development and Application of Power Time-Sensitive Network Switching Chip。
文摘The progress of modern industry has given rise to great requirements for network transmission latency and reliability in domains such as smart grid and intelligent driving.To address these challenges,the concept of Time-sensitive networking(TSN)is proposed by IEEE 802.1TSN working group.In order to achieve low latency,Cyclic queuing and forwarding(CQF)mechanism is introduced to schedule Timetriggered(TT)flows.In this paper,we construct a TSN model based on CQF and formulate the flow scheduling problem as an optimization problem aimed at maximizing the success rate of flow scheduling.The problem is tackled by a novel algorithm that makes full use of the characteristics and the relationship between the flows.Firstly,by K-means algorithm,the flows are initially partitioned into subsets based on their correlations.Subsequently,the flows within each subset are sorted by a new special criteria extracted from multiple features of flow.Finally,a flow offset selecting method based on load balance is used for resource mapping,so as to complete the process of flow scheduling.Experimental results demonstrate that the proposed algorithm exhibits significant advantages in terms of scheduling success rate and time efficiency.
文摘The somatotopic representation of specific body parts is a well-established spatial organizational principle in the primary somatosensory and motor cortices.
基金supported by the National Natural Science Foundation of China(61172116)
文摘The main function of electronic support measure system is to detect threating signals in order to take countermeasures against them. To accomplish this objective, a process of associating each interleaved pulse with its emitter must be done. This process is termed sorting or de-interleaving. A novel point symmetry based radar sorting (PSBRS) algorithm is addressed. In order to deal with all kinds of radar signals, the symmetry measure distance is used to cluster pulses instead of the conventional Euclidean distance. The reference points of the symmetrical clusters are initialized by the alternative fuzzy c-means (AFCM) algorithm to ameliorate the effects of noise and the false sorting. Besides, the density filtering (DF) algorithm is proposed to discard the noise pulses or clutter. The performance of the algorithm is evaluated under the effects of noise and missing pulses. It has been observed that the PSBRS algorithm can cope with a large number of noise pulses and it is completely independent of missing pulses. Finally, PSBRS is compared with some benchmark algorithms, and the simulation results reveal the feasibility and efficiency of the algorithm.
基金Project supported by the National Basic Research Program of China (973 Program) (No. 2007CB714600)
文摘The non-dominated sorting genetic algorithm （NSGA） is improved with the controlled elitism and dynamic crowding distance. A novel multi-objective optimization algorithm is obtained for wind turbine blades. As an example, a 5 MW wind turbine blade design is presented by taking the maximum power coefficient and the minimum blade mass as the optimization objectives. The optimal results show that this algorithm has good performance in handling the multi-objective optimization of wind turbines, and it gives a Pareto-optimal solution set rather than the optimum solutions to the conventional multi objective optimization problems. The wind turbine blade optimization method presented in this paper provides a new and general algorithm for the multi-objective optimization of wind turbines.
基金supported by the National Science and Technology Support Program of China(No.2012BAC11B07)the Jiangxi Science and Technology Innovation Base Plan(No.20212BCD42017)。
文摘Under the background of increasingly scarce ore worldwide and increasingly fierce market competition,developing the mining industry could be strongly restricted.Intelligent ore sorting equipment not only improves ore use and enhances the economic benefits of enterprises but also increases the ore grade and lessens the grinding cost and tailings production.However,long-term research on intelligent ore sorting equipment found that the factors affecting sorting efficiency mainly include ore information identification technology,equipment sorting actuator,and information processing algorithm.The high precision,strong anti-interference capability,and high speed of these factors guarantee the separation efficiency of intelligent ore sorting equipment.Color ore sorter,X-ray ore transmission sorter,dual-energy X-ray transmission ore sorter,X-ray fluorescence ore sorter,and near-infrared ore sorter have been successfully developed in accordance with the different characteristics of minerals while ensuring the accuracy of equipment sorting and improving the equipment sorting efficiency.With the continuous improvement of mine automation level,the application of online element rapid analysis technology with high speed,high precision,and strong anti-interference capability in intelligent ore sorting equipment will become an inevitable trend of equipment development in the future.Laser-induced breakdown spectroscopy,transientγneutron activation analysis,online Fourier transform infrared spectroscopy,and nuclear magnetic resonance techniques will promote the development of ore sorting equipment.In addition,the improvement and joint application of additional high-speed and high-precision operation algorithms(such as peak area,principal component analysis,artificial neural network,partial least squares,and Monte Carlo library least squares methods)are an essential part of the development of intelligent ore sorting equipment in the future.
基金supported by the National Natural Science Foundation of China (60872108)the Postdoctoral Science Foundation of China(200902411+3 种基金20080430903)Heilongjiang Postdoctoral Financial Assistance (LBH-Z08129)the Scientific and Technological Creative Talents Special Research Foundation of Harbin Municipality (2008RFQXG030)Central University Basic Research Professional Expenses Special Fund Project
文摘A novel class of periodically changing features hidden in radar pulse sequence environment,named G features,is proposed.Combining fractal theory and Hilbert-Huang transform,the features are extracted using changing characteristics of pulse parameters in radar emitter signals.The features can be applied in modern complex electronic warfare environment to address the issue of signal sorting when radar emitter pulse signal parameters severely or even completely overlap.Experiment results show that the proposed feature class and feature extraction method can discriminate periodically changing pulse sequence signal sorting features from radar pulse signal flow with complex variant features,therefore provide a new methodology for signal sorting.
