查看更多>>摘要：Emerging applications such as smart city infrastructures and virtual reality landscapes are set-ting rigorous benchmarks for 6G mobile networks,requiring elevated levels of confidentiality,integrity,non-repudiation,authentication,and stringent access controls.Blockchain technology is heralded as a transforma-tive enabler for meeting 6G standards,owing to its intrinsic attributes.However,a gap exists in the holistic investigation of blockchain's applicability in 6G realms,particularly addressing the"whether","when",and"how"of its deployment.Present research trails in developing robust methodologies to gauge blockchain's efficacy within 6G use cases.Addressing this,our study introduces a novel confluence of blockchain with 6G networks,where data resides in distributed Hash tables(DHTs)while their hashes are secured in distributed ledger technology(DLT),harnessing blockchain's core strengths-immutability,traceability,and fortified se-curity.We delineate seven specific 6G use cases poised for enhancement through blockchain integration,and scrutinize the rationale,nature,and timing of this convergence.Furthermore,we devise a comprehen-sive methodology for assessing blockchain's performance metrics and scalability in 6G environments.Our extensive experimental analyses evaluate the synergistic performance of this integration,revealing that the Quorum blockchain satisfactorily supports 80％of 6G scenarios.The findings suggest that,with appropriate configurations,consortium blockchains are well-equipped to fulfill the demanding performance and scalability requisites of 6G networks.
Kai FANGJunxin CHENHan ZHUThippa Reddy GADEKALLU...
23-41页
查看更多>>摘要：Artificial intelligence technology is widely used in the field of wireless sensor networks(WSN).Due to its inexplicability,the interference factors in the process of WSN object localization cannot be ef-fectively eliminated.In this paper,an explainable-AI-based two-stage solution is proposed for WSN object localization.In this solution,mobile transceivers are used to enlarge the positioning range and eliminate the blind area for object localization.The motion parameters of transceivers are considered to be unavailable,and the localization problem is highly nonlinear with respect to the unknown parameters.To address this,an explainable AI model is proposed to solve the localization problem.Since the relationship among the variables is difficult to fully include in the first-stage traditional model,we develop a two-stage explainable AI solution for this localization problem.The two-stage solution is actually a comprehensive consideration of the relationship between variables.The solution can continue to use the constraints unused in the first-stage during the second-stage,thereby improving the performance of the solution.Therefore,the two-stage solution has stronger robustness compared to the closed-form solution.Experimental results show that the performance of both the two-stage solution and the traditional solution will be affected by numerical changes in unknown parameters.However,the two-stage solution performs better than the traditional solution,espe-cially with a small number of mobile transceivers and sensors or in the presence of high noise.Furthermore,we have also verified the feasibility of the proposed explainable-AI-based two-stage solution.
查看更多>>摘要：Content delivery networks(CDNs)play a pivotal role in the modern internet infrastructure by enabling efficient content delivery across diverse geographical regions.As an essential component of CDNs,the edge caching scheme directly influences the user experience by determining the caching and eviction of content on edge servers.With the emergence of 5G technology,traditional caching schemes have faced challenges in adapting to increasingly complex and dynamic network environments.Consequently,deep reinforcement learning(DRL)offers a promising solution for intelligent zero-touch network governance.However,the black-box nature of DRL models poses challenges in understanding and making trusting decisions.In this paper,we propose an explainable reinforcement learning(XRL)-based intelligent edge service caching approach,namely XRL-SHAP-Cache,which combines DRL with an explainable artificial intelligence(XAI)technique for cache management in CDNs.Instead of focusing solely on achieving performance gains,this study introduces a novel paradigm for providing interpretable caching strategies,thereby establishing a foundation for future transparent and trustworthy edge caching solutions.Specifically,a multi-level cache scheduling framework for CDNs was formulated theoretically,with the D3QN-based caching scheme serving as the targeted interpretable model.Subsequently,by integrating Deep-SHAP into our framework,the contribution of each state input feature to the agent's Q-value output was calculated,thereby providing valuable insights into the decision-making process.The proposed XRL-SHAP-Cache approach was evaluated through extensive experiments to demonstrate the behavior of the scheduling agent in the face of different environmental inputs.The results demonstrate its strong explainability under various real-life scenarios while maintaining superior performance compared to traditional caching schemes in terms of cache hit ratio,quality of service(QoS),and space utilization.
查看更多>>摘要：With the rapid development of network technology and the automation process for 5G,cyber-attacks have become increasingly complex and threatening.In response to these threats,researchers have developed various network intrusion detection systems(NIDS)to monitor network traffic.However,the incessant emergence of new attack techniques and the lack of system interpretability pose challenges to im-proving the detection performance of NIDS.To address these issues,this paper proposes a hybrid explainable neural network-based framework that improves both the interpretability of our model and the performance in detecting new attacks through the innovative application of the explainable artificial intelligence(XAI)method.We effectively introduce the Shapley additive explanations(SHAP)method to explain a light gra-dient boosting machine(LightGBM)model.Additionally,we propose an autoencoder long-term short-term memory(AE-LSTM)network to reconstruct SHAP values previously generated.Furthermore,we define a threshold based on reconstruction errors observed during the training phase.Any network flow that sur-passes the specified threshold is classified as an attack flow.This approach enhances the framework's ability to accurately identify attacks.We achieve an accuracy of 92.65％,a recall of 95.26％,a precision of 92.57％,and an F1-score of 93.90％on the dataset NSL-KDD.Experimental results demonstrate that our approach generates detection performance on par with state-of-the-art methods.
查看更多>>摘要：Classifying network time series(NTS)is crucial for automating network administration and ensuring cyberspace security.It enables the detection of anomalies,the identification of network attacks,and the monitoring of performance issues,thereby providing valuable support for network protection and optimization.However,modern communication networks pose challenges for NTS classification methods.These include handling large-scale and complex NTS data,extracting features from intricate datasets,and addressing explainability requirements.These challenges are particularly pronounced for complex 5G net-works.Notably,explainability has become crucial for the widespread deployment of network automation for 5G networks and beyond.To tackle these challenges,we propose a path-signature-based NTS classi-fication model called recurrent signature(RecurSig).This innovative model is designed to overcome the time-consuming feature selection problem by utilizing deep-learning(DL)techniques.Additionally,it pro-vides a solution for addressing the black-box issue associated with DL models in network automation systems(NAS)by incorporating an explainable classification approach.Extensive experimentation on various public datasets demonstrates that RecurSig outperforms existing models in accuracy and explainability.The results indicate its potential for application in cyberspace security and automated network management,offering an explainable solution for network protection and optimization.
查看更多>>摘要：Mobile telemedicine systems based on the next-generation communication will significantly en-hance deep fusion of network automation and federated learning(FL),but data privacy is a paramount issue in sectors like healthcare.This work hence considers FL augments 5G-and-beyond networks by training deep learning(DL)models without the need to exchange raw data.The substantial communication loads imposed on by extensive parameters involved in DL models are managed through adaptive scheduling mechanisms effectively.To address the opaque nature of DL models and to improve the interpretability of FL models,we introduce a convolutional fuzzy rough neural network specifically designed for medical image processing.We also develop a multiobjective memetic evolutionary algorithm to streamline and optimize the neural network architectures.Our comprehensive FL framework integrates smart scheduling,interpretable fuzzy rough logic,and neuroevolution.This framework is shown to improve communication efficiency,increase interpretability of diagnosis with protected privacy,and generate low-complexity neural architectures.
查看更多>>摘要：Game theory studies the mathematical models for self-interested individuals.Nash equilibrium is arguably the most central solution in game theory.While finding the Nash equilibrium in general is known as polynomial parity arguments on directed graphs(PPAD)-complete,learning in games provides an alternative to approximate Nash equilibrium,which iteratively updates the player's strategy through interactions with other players.Rules and models have been developed for learning in games,such as fictitious play and no-regret learning.Particularly,with recent advances in online learning and deep reinforcement learning,techniques from these fields greatly boost the breakthroughs in learning in games from theory to application.As a result,we have witnessed many superhuman game AI systems.The techniques used in these systems evolve from conventional search and learning to purely reinforcement learning(RL)-style learning methods,gradually getting rid of the domain knowledge.In this article,we systematically review the above techniques,discuss the trend of basic learning rules towards a unified framework,and recap applications in large games.Finally,we discuss some future directions and make the prospect of future game AI systems.We hope this article will give some insights into designing novel approaches.
查看更多>>摘要：Binary neural networks have become a promising research topic due to their advantages of fast inference speed and low energy consumption.However,most existing studies focus on binary convolutional neural networks,while less attention has been paid to binary graph neural networks.A common drawback of existing studies on binary graph neural networks is that they still include lots of inefficient full-precision operations in multiplying three matrices and are therefore not efficient enough.In this paper,we propose a novel method,called re-quantization-based binary graph neural networks(RQBGN),for binarizing graph neural networks.Specifically,re-quantization,a necessary procedure contributing to the further reduction of superfluous inefficient full-precision operations,quantizes the results of multiplication between any two matrices during the process of multiplying three matrices.To address the challenges introduced by re-quantization,in RQBGN we first study the impact of different computation orders to find an effective one and then introduce a mixture of experts to increase the model capacity.Experiments on five benchmark datasets show that performing re-quantization in different computation orders significantly impacts the performance of binary graph neural network models,and RQBGN can outperform other baselines to achieve state-of-the-art performance.
查看更多>>摘要：Adversarial implementations of cryptographic primitives called kleptographic attacks cause the leakage of secret information.Subliminal channel attacks are one of the kleptographic attacks.In such attacks,backdoors are embedded in implementations of randomized algorithms to elaborately control ran-domness generation,such that the secrets will be leaked from biased outputs.To thwart subliminal channel attacks,double-splitting is a feasible solution,which splits the randomness generator of a randomized algo-rithm into two independent generators.In this paper,we instantiate double-splitting to propose a secure randomness generation algorithm dubbed SRG using two physically independent generators:ordinary and public randomness generators.Based on public blockchains,we construct the public randomness generator,which can be verified publicly.Hashes of a sufficient number of consecutive blocks that are newly confirmed on a blockchain are used to produce public randomness.In SRG,outputs from the two generators are taken as inputs of an immunization function.SRG accomplishes immunization against subliminal channel attacks.Additionally,we discuss the application strategies of SRG for symmetric and public-key encryption.
查看更多>>摘要：Recent advancements in attribute localization have showcased its potential in discovering the intrinsic semantic knowledge for visual feature representations,thereby facilitating significant visual-semantic interactions essential for zero-shot learning(ZSL).However,the majority of existing attribute localization methods heavily rely on classification constraints,resulting in accurate localization of only a few attributes while neglecting the rest important attributes associated with other classes.This limitation hinders the discovery of the intrinsic semantic relationships between attributes and visual features across all classes.To address this problem,we propose a novel attribute localization refinement(ALR)module designed to enhance the model's ability to accurately localize all attributes.Essentially,we enhance weak discriminant attributes by grouping them and introduce weighted attribute regression to standardize the mapping values of semantic attributes.This module can be flexibly combined with existing attribute localization methods.Our experiments show that when combined with the ALR module,the localization errors in existing methods are corrected,and state-of-the-art classification performance is achieved.
NETL
NSTL
万方数据