Multi-Source data plays an important role in the evolution of media convergence.Its fusion processing enables the further mining of data and utilization of data value and broadens the path for the sharing and dissemin...Multi-Source data plays an important role in the evolution of media convergence.Its fusion processing enables the further mining of data and utilization of data value and broadens the path for the sharing and dissemination of media data.However,it also faces serious problems in terms of protecting user and data privacy.Many privacy protectionmethods have been proposed to solve the problemof privacy leakage during the process of data sharing,but they suffer fromtwo flaws:1)the lack of algorithmic frameworks for specific scenarios such as dynamic datasets in the media domain;2)the inability to solve the problem of the high computational complexity of ciphertext in multi-source data privacy protection,resulting in long encryption and decryption times.In this paper,we propose a multi-source data privacy protection method based on homomorphic encryption and blockchain technology,which solves the privacy protection problem ofmulti-source heterogeneous data in the dissemination ofmedia and reduces ciphertext processing time.We deployed the proposedmethod on theHyperledger platformfor testing and compared it with the privacy protection schemes based on k-anonymity and differential privacy.The experimental results showthat the key generation,encryption,and decryption times of the proposedmethod are lower than those in data privacy protection methods based on k-anonymity technology and differential privacy technology.This significantly reduces the processing time ofmulti-source data,which gives it potential for use in many applications.展开更多
Most studies have conducted experiments on predicting energy consumption by integrating data formodel training.However, the process of centralizing data can cause problems of data leakage.Meanwhile,many laws and regul...Most studies have conducted experiments on predicting energy consumption by integrating data formodel training.However, the process of centralizing data can cause problems of data leakage.Meanwhile,many laws and regulationson data security and privacy have been enacted, making it difficult to centralize data, which can lead to a datasilo problem. Thus, to train the model while maintaining user privacy, we adopt a federated learning framework.However, in all classical federated learning frameworks secure aggregation, the Federated Averaging (FedAvg)method is used to directly weight the model parameters on average, which may have an adverse effect on te model.Therefore, we propose the Federated Reinforcement Learning (FedRL) model, which consists of multiple userscollaboratively training the model. Each household trains a local model on local data. These local data neverleave the local area, and only the encrypted parameters are uploaded to the central server to participate in thesecure aggregation of the global model. We improve FedAvg by incorporating a Q-learning algorithm to assignweights to each locally uploaded local model. And the model has improved predictive performance. We validatethe performance of the FedRL model by testing it on a real-world dataset and compare the experimental results withother models. The performance of our proposed method in most of the evaluation metrics is improved comparedto both the centralized and distributed models.展开更多
The COVID-19 pandemic accelerated the acceptance of digital banking services such as online payment and banking apps.As bank clients become more likely to use online services and contactless payment,the amount of cons...The COVID-19 pandemic accelerated the acceptance of digital banking services such as online payment and banking apps.As bank clients become more likely to use online services and contactless payment,the amount of consumer data available for banks’digitalization strategies has increased.This acceleration in digital banking has placed a spotlight on retail banks’efforts to protect personal data.Bank staff are on the frontlines of both protecting personal data and communicating their banks’efforts in this respect to maintain consumer trust.Our study aimed to answer the following question:How did the sudden increase in digitalization during the pandemic affect bank staff’s capabilities in protecting personal data?In a two-stage qualitative study,we collected empirical data on bank staff’s data protection efforts during accelerated digitalization.Analyzing our findings from the perspective of technological mediation theory,which focuses on the relationships between technologies,practices,and social arrangements,we found that in banking platformization,bank staff are disempowered in supporting clients,who are responsibilized for protecting themselves from fraud.Competitive pressures push retail banks into using client data in ways beyond sector norms,endangering the contextual integrity of data flows.Further,our findings show that digitalization presents bank clients with new risks,of which they are informed only after changing their banking practices,and it may be difficult to return to former arrangements.The application of mediation theory,combined with contextual integrity theory,clarified the shifting positions of different digital technology users in the infrastructural network of platformized banking and allowed for an in-depth analysis of conflicting interests.By clarifying these interests,difficulties were identified that need to be addressed in public policy and digital innovation projects to prevent loss of trust among bank clients.展开更多
As Vehicular ad hoc networks (VANETs) become more sophisticated, the importance of integrating data protection and cybersecurity is increasingly evident. This paper offers a comprehensive investigation into the challe...As Vehicular ad hoc networks (VANETs) become more sophisticated, the importance of integrating data protection and cybersecurity is increasingly evident. This paper offers a comprehensive investigation into the challenges and solutions associated with the privacy implications within VANETs, rooted in an intricate landscape of cross-jurisdictional data protection regulations. Our examination underscores the unique nature of VANETs, which, unlike other ad-hoc networks, demand heightened security and privacy considerations due to their exposure to sensitive data such as vehicle identifiers, routes, and more. Through a rigorous exploration of pseudonymization schemes, with a notable emphasis on the Density-based Location Privacy (DLP) method, we elucidate the potential to mitigate and sometimes sidestep the heavy compliance burdens associated with data protection laws. Furthermore, this paper illuminates the cybersecurity vulnerabilities inherent to VANETs, proposing robust countermeasures, including secure data transmission protocols. In synthesizing our findings, we advocate for the proactive adoption of protective mechanisms to facilitate the broader acceptance of VANET technology while concurrently addressing regulatory and cybersecurity hurdles.展开更多
With the evolution of next-generation communication networks,ensuring robust Core Network(CN)architecture and data security has become paramount.This paper addresses critical vulnerabilities in the architecture of CN ...With the evolution of next-generation communication networks,ensuring robust Core Network(CN)architecture and data security has become paramount.This paper addresses critical vulnerabilities in the architecture of CN and data security by proposing a novel framework based on blockchain technology that is specifically designed for communication networks.Traditional centralized network architectures are vulnerable to Distributed Denial of Service(DDoS)attacks,particularly in roaming scenarios where there is also a risk of private data leakage,which imposes significant operational demands.To address these issues,we introduce the Blockchain-Enhanced Core Network Architecture(BECNA)and the Secure Decentralized Identity Authentication Scheme(SDIDAS).The BECNA utilizes blockchain technology to decentralize data storage,enhancing network security,stability,and reliability by mitigating Single Points of Failure(SPoF).The SDIDAS utilizes Decentralized Identity(DID)technology to secure user identity data and streamline authentication in roaming scenarios,significantly reducing the risk of data breaches during cross-network transmissions.Our framework employs Ethereum,free5GC,Wireshark,and UERANSIM tools to create a robust,tamper-evident system model.A comprehensive security analysis confirms substantial improvements in user privacy and network security.Simulation results indicate that our approach enhances communication CNs security and reliability,while also ensuring data security.展开更多
Due to the fact that a memristor with memory properties is an ideal electronic component for implementation of the artificial neural synaptic function,a brand-new tristable locally active memristor model is first prop...Due to the fact that a memristor with memory properties is an ideal electronic component for implementation of the artificial neural synaptic function,a brand-new tristable locally active memristor model is first proposed in this paper.Here,a novel four-dimensional fractional-order memristive cellular neural network(FO-MCNN)model with hidden attractors is constructed to enhance the engineering feasibility of the original CNN model and its performance.Then,its hardware circuit implementation and complicated dynamic properties are investigated on multi-simulation platforms.Subsequently,it is used toward secure communication application scenarios.Taking it as the pseudo-random number generator(PRNG),a new privacy image security scheme is designed based on the adaptive sampling rate compressive sensing(ASR-CS)model.Eventually,the simulation analysis and comparative experiments manifest that the proposed data encryption scheme possesses strong immunity against various security attack models and satisfactory compression performance.展开更多
Transfer learning is an effective method to predict the energy consumption of information-poor buildings by learning transferable knowledge from operational data of information-rich buildings.However,it is not recomme...Transfer learning is an effective method to predict the energy consumption of information-poor buildings by learning transferable knowledge from operational data of information-rich buildings.However,it is not recommended to directly use the operational data without protection due to the risk of leaking occupants’privacy.To address this problem,this study proposes a federated learning-based method to learn transferable knowledge from building operational data without privacy leaking.It trains a transferable federated model based on the operational data from the buildings similar to the target building with limited data.An advanced secure aggregation algorithm is adopted in the training process to ensure that no one can infer private information from the training data.The federated model obtained is evaluated by comparing it with the standalone model without federated learning based on 13 similar office buildings from the Building Data Genome Project.The results show that the federated model outperforms the standalone model concerning the prediction accuracy and training time.On average,the federated model achieves a 25.4%decrease in CV-RMSE when the target building has limited operational data.Even if the target building has no operational data,the federated model still achieves acceptable accuracy(CV-RMSE is 22.2%).Meanwhile,the training time of the federated model is 90%less than that of the standalone model.The research insights can help develop federated learning-based methods for solving the data silos problem in building energy management.The methodology and analysis procedures are reproducible and all codes and data sets are available on Github.展开更多
基金funded by the High-Quality and Cutting-Edge Discipline Construction Project for Universities in Beijing (Internet Information,Communication University of China).
文摘Multi-Source data plays an important role in the evolution of media convergence.Its fusion processing enables the further mining of data and utilization of data value and broadens the path for the sharing and dissemination of media data.However,it also faces serious problems in terms of protecting user and data privacy.Many privacy protectionmethods have been proposed to solve the problemof privacy leakage during the process of data sharing,but they suffer fromtwo flaws:1)the lack of algorithmic frameworks for specific scenarios such as dynamic datasets in the media domain;2)the inability to solve the problem of the high computational complexity of ciphertext in multi-source data privacy protection,resulting in long encryption and decryption times.In this paper,we propose a multi-source data privacy protection method based on homomorphic encryption and blockchain technology,which solves the privacy protection problem ofmulti-source heterogeneous data in the dissemination ofmedia and reduces ciphertext processing time.We deployed the proposedmethod on theHyperledger platformfor testing and compared it with the privacy protection schemes based on k-anonymity and differential privacy.The experimental results showthat the key generation,encryption,and decryption times of the proposedmethod are lower than those in data privacy protection methods based on k-anonymity technology and differential privacy technology.This significantly reduces the processing time ofmulti-source data,which gives it potential for use in many applications.
基金supported by National Key R&D Program of China(No.2020YFC2006602)National Natural Science Foundation of China(Nos.62172324,62072324,61876217,6187612)+2 种基金University Natural Science Foundation of Jiangsu Province(No.21KJA520005)Primary Research and Development Plan of Jiangsu Province(No.BE2020026)Natural Science Foundation of Jiangsu Province(No.BK20190942).
文摘Most studies have conducted experiments on predicting energy consumption by integrating data formodel training.However, the process of centralizing data can cause problems of data leakage.Meanwhile,many laws and regulationson data security and privacy have been enacted, making it difficult to centralize data, which can lead to a datasilo problem. Thus, to train the model while maintaining user privacy, we adopt a federated learning framework.However, in all classical federated learning frameworks secure aggregation, the Federated Averaging (FedAvg)method is used to directly weight the model parameters on average, which may have an adverse effect on te model.Therefore, we propose the Federated Reinforcement Learning (FedRL) model, which consists of multiple userscollaboratively training the model. Each household trains a local model on local data. These local data neverleave the local area, and only the encrypted parameters are uploaded to the central server to participate in thesecure aggregation of the global model. We improve FedAvg by incorporating a Q-learning algorithm to assignweights to each locally uploaded local model. And the model has improved predictive performance. We validatethe performance of the FedRL model by testing it on a real-world dataset and compare the experimental results withother models. The performance of our proposed method in most of the evaluation metrics is improved comparedto both the centralized and distributed models.
文摘The COVID-19 pandemic accelerated the acceptance of digital banking services such as online payment and banking apps.As bank clients become more likely to use online services and contactless payment,the amount of consumer data available for banks’digitalization strategies has increased.This acceleration in digital banking has placed a spotlight on retail banks’efforts to protect personal data.Bank staff are on the frontlines of both protecting personal data and communicating their banks’efforts in this respect to maintain consumer trust.Our study aimed to answer the following question:How did the sudden increase in digitalization during the pandemic affect bank staff’s capabilities in protecting personal data?In a two-stage qualitative study,we collected empirical data on bank staff’s data protection efforts during accelerated digitalization.Analyzing our findings from the perspective of technological mediation theory,which focuses on the relationships between technologies,practices,and social arrangements,we found that in banking platformization,bank staff are disempowered in supporting clients,who are responsibilized for protecting themselves from fraud.Competitive pressures push retail banks into using client data in ways beyond sector norms,endangering the contextual integrity of data flows.Further,our findings show that digitalization presents bank clients with new risks,of which they are informed only after changing their banking practices,and it may be difficult to return to former arrangements.The application of mediation theory,combined with contextual integrity theory,clarified the shifting positions of different digital technology users in the infrastructural network of platformized banking and allowed for an in-depth analysis of conflicting interests.By clarifying these interests,difficulties were identified that need to be addressed in public policy and digital innovation projects to prevent loss of trust among bank clients.
文摘As Vehicular ad hoc networks (VANETs) become more sophisticated, the importance of integrating data protection and cybersecurity is increasingly evident. This paper offers a comprehensive investigation into the challenges and solutions associated with the privacy implications within VANETs, rooted in an intricate landscape of cross-jurisdictional data protection regulations. Our examination underscores the unique nature of VANETs, which, unlike other ad-hoc networks, demand heightened security and privacy considerations due to their exposure to sensitive data such as vehicle identifiers, routes, and more. Through a rigorous exploration of pseudonymization schemes, with a notable emphasis on the Density-based Location Privacy (DLP) method, we elucidate the potential to mitigate and sometimes sidestep the heavy compliance burdens associated with data protection laws. Furthermore, this paper illuminates the cybersecurity vulnerabilities inherent to VANETs, proposing robust countermeasures, including secure data transmission protocols. In synthesizing our findings, we advocate for the proactive adoption of protective mechanisms to facilitate the broader acceptance of VANET technology while concurrently addressing regulatory and cybersecurity hurdles.
基金supported by the Beijing Natural Science Foundation(L223025,4242003)Qin Xin Talents Cultivation Program of Beijing Information Science&Technology University(QXTCP B202405)。
文摘With the evolution of next-generation communication networks,ensuring robust Core Network(CN)architecture and data security has become paramount.This paper addresses critical vulnerabilities in the architecture of CN and data security by proposing a novel framework based on blockchain technology that is specifically designed for communication networks.Traditional centralized network architectures are vulnerable to Distributed Denial of Service(DDoS)attacks,particularly in roaming scenarios where there is also a risk of private data leakage,which imposes significant operational demands.To address these issues,we introduce the Blockchain-Enhanced Core Network Architecture(BECNA)and the Secure Decentralized Identity Authentication Scheme(SDIDAS).The BECNA utilizes blockchain technology to decentralize data storage,enhancing network security,stability,and reliability by mitigating Single Points of Failure(SPoF).The SDIDAS utilizes Decentralized Identity(DID)technology to secure user identity data and streamline authentication in roaming scenarios,significantly reducing the risk of data breaches during cross-network transmissions.Our framework employs Ethereum,free5GC,Wireshark,and UERANSIM tools to create a robust,tamper-evident system model.A comprehensive security analysis confirms substantial improvements in user privacy and network security.Simulation results indicate that our approach enhances communication CNs security and reliability,while also ensuring data security.
文摘Due to the fact that a memristor with memory properties is an ideal electronic component for implementation of the artificial neural synaptic function,a brand-new tristable locally active memristor model is first proposed in this paper.Here,a novel four-dimensional fractional-order memristive cellular neural network(FO-MCNN)model with hidden attractors is constructed to enhance the engineering feasibility of the original CNN model and its performance.Then,its hardware circuit implementation and complicated dynamic properties are investigated on multi-simulation platforms.Subsequently,it is used toward secure communication application scenarios.Taking it as the pseudo-random number generator(PRNG),a new privacy image security scheme is designed based on the adaptive sampling rate compressive sensing(ASR-CS)model.Eventually,the simulation analysis and comparative experiments manifest that the proposed data encryption scheme possesses strong immunity against various security attack models and satisfactory compression performance.
基金supported by the National Key Research and Development Program of China(No.2018YFE0116300)the National Natural Science Foundation of China(No.51978601).
文摘Transfer learning is an effective method to predict the energy consumption of information-poor buildings by learning transferable knowledge from operational data of information-rich buildings.However,it is not recommended to directly use the operational data without protection due to the risk of leaking occupants’privacy.To address this problem,this study proposes a federated learning-based method to learn transferable knowledge from building operational data without privacy leaking.It trains a transferable federated model based on the operational data from the buildings similar to the target building with limited data.An advanced secure aggregation algorithm is adopted in the training process to ensure that no one can infer private information from the training data.The federated model obtained is evaluated by comparing it with the standalone model without federated learning based on 13 similar office buildings from the Building Data Genome Project.The results show that the federated model outperforms the standalone model concerning the prediction accuracy and training time.On average,the federated model achieves a 25.4%decrease in CV-RMSE when the target building has limited operational data.Even if the target building has no operational data,the federated model still achieves acceptable accuracy(CV-RMSE is 22.2%).Meanwhile,the training time of the federated model is 90%less than that of the standalone model.The research insights can help develop federated learning-based methods for solving the data silos problem in building energy management.The methodology and analysis procedures are reproducible and all codes and data sets are available on Github.
