With the flourishing of the Agricultural Internet of Things (AIoT), analyzing large-volume sensor data has become a regular requirement for agricultural decision-making. Federated learning (FL), which facilitates scattered AIoT devices to train models collaboratively, has gained significant attention. However, traditional FL poses challenges in AIoT scenarios, such as wide geo-distribution, heterogeneous data distribution, and high-device risks. Existing works tend to be one-sided and remain unclear on how to tackle these issues thoroughly in AIoT. To fill the gap, we presentBc(2)FL, a double-layer blockchain-based FL framework, which enhances both learning efficiency and security for AIoT. The double-layer blockchain, coupled with a two-stage consensus algorithm, drives the hierarchical FL process to enable efficient and reliable agricultural knowledge-sharing. In addition, Bc(2)FL adopts an adaptive model aggregation algorithm to dynamically tune noise levels based on the model quality, further improving the learning security and model credibility. Finally, the extensive experimental results demonstrate that Bc(2)FL not only improves the model accuracy by up to 21.17% compared with the state-of-the-art baselines, but also enhances the privacy protection within an additional error of only 2.1%.

With the increasing growth of data scale and computing complexity, Flink, a novel distributed computing system, has been applied in various scenarios (e.g., machine learning) due to its excellent iterative nature. Predicting the runtime of Flink iterative jobs is critical to optimizing their performance. However, existing offline works generally ignore relevant runtime information, such as cluster state variations and inter-iteration dependencies, resulting in high actual prediction errors. Online methods, on the other hand, have a non-negligible time overhead. In light of this, we propose TimeLink, a dynamic runtime prediction algorithm for Flink iterative jobs. Its key idea consists of three stages: (1) TimeLink incorporates both offline and online execution features during runtime to measure the fine-grained similarity of iterative jobs, (2) it matches historical jobs with similar performance consumption to the current running iterative job in real time, and (3) its remaining runtime is predicted by combining the continuity of runtime bias between completed supersteps of matched jobs and the current iterative job. We implement TimeLink and evaluate it using realistic iterative workloads. The experimental results show that TimeLink exhibits relative average prediction errors of 5.91–12.86

With the continuous advancement of cloud computing and satellite communication technology, the cloud-network-integrated satellite network has emerged as a novel network architecture. This architecture harnesses the benefits of cloud computing and satellite communication to achieve global coverage, high reliability, and flexible information services. However, as business types and user demands grow, addressing differentiated Quality of Service (QoS) requirements has become a crucial challenge for cloud-network-integrated satellite networks. Effective resource allocation algorithms are essential to meet these differentiated QoS requirements. Currently, research on resource allocation algorithms for differentiated QoS requirements in cloud-network-integrated satellite networks is still in its early stages. While some research results have been achieved, there persist issues such as high algorithm complexity, limited practicality, and a lack of effective evaluation and adjustment mechanisms. The first part of this study examines the state of research on network virtual mapping methods that are currently in use. A reinforcement-learning-based virtual network mapping approach that considers quality of service is then suggested. This algorithm aims to improve user QoS and request acceptance ratio by introducing QoS satisfaction parameters. With the same computational complexity, QoS is significantly improved. Additionally, there has been a noticeable improvement in the request acceptance ratio and resource utilization efficiency. The proposed algorithm solves existing challenges and takes a step towards more practical and efficient resource allocation in cloud-network-integrated satellite networks. Experiments have proven the practicality of the proposed virtual network embedding algorithm of Satellite Network (SN-VNE) based on Reinforcement Learning (RL) in meeting QoS and improving utilization of limited heterogeneous resources. We contrast the performance of the SN-VNE algorithm with DDRL-VNE, CDRL, and DSCD-VNE. Our algorithm improve the acceptance ratio of VNEs, long-term average revenue and delay by an average of 7.9%, 15.87%, and 63.21%, respectively.

本文以国家一流本科专业电子商务专业核心课程之一《网络营销》为探索与实践对象,从整体布局、课程内容重构、课程内容建设和线上线下混合式综合考评体系等方面,对"SPOC+课程思政"的混合式教学设计进行了探索与实践,希望对于其它专业核心课程的建设具有一定的借鉴和参考意义.

数字经济时代,数据分析类课程已经被广泛纳入各类院校的专业课程体系中,成为培养经济与管理相关专业学生大数据处理能力、提升当代大学生数据基本素养的专业性课程,但在"大思政课"建设背景下,数据分析类课程思政依然存在"贴标签""刻意化"等问题.鉴于此,首先,梳理数据分析类课程的发展历程和特征;其次,分析制约数据分析类课程思政建设的因素;最后,从3 个维度探讨经管专业数据分析类课程思政的推进路径.

Deep learning models are a valuable "secret sauce" that confers a significant competitive advantage. Many models are never visible to the user and even publicly known state-of-the-art models are either completely proprietary or only accessible via access-controlled APIs. Increasingly, these models run directly on the edge, often using a low-power DNN accelerator. This makes models particularly vulnerable, as an attacker with physical access can exploit side channels like off-chip memory access volumes. Indeed, prior work has shown that this channel can be used to steal dense DNNs from edge devices by correlating data transfer volumes with layer geometry. Unfortunately, prior techniques become intractable when the model is sparse in either weights or activations because off-chip transfers no longer correspond exactly to layer dimensions. Could it be that the many mobile-class sparse accelerators are inherently safe from this style of attack? In this paper, we show that it is feasible to steal a pruned DNN model architecture from a mobile-class sparse accelerator using the DRAM access volume channel. We describe HuffDuff, an attack scheme with two novel techniques that leverage (i) the boundary effect present in CONV layers, and (ii) the timing side channel of on-the-fly activation compression. Together, these techniques dramatically reduce the space of possible model architectures up to 94 orders of magnitude, resulting in fewer than 100 candidate models - a number that can be feasibly tested. Finally, we sample network instances from our solution space and show that (i) our solutions reach the victim accuracy under the iso-footprint constraint, and (ii) significantly improve black-box targeted attack success rates.

Federated learning (FL) has become a new form of data sharing by aggregating multi-party local models. Although the existing FL incentive system has reduced insufficient data supply under comprehensive information, it still confronts issues including free-riding, unfairness, and unreliability. Therefore, this paper proposes an incomplete information FL incentive mechanism based on blockchain and Bayesian games. The data transaction process is modeled by quantifying the cost-utility of the data providers and the payment reward of the data requesters, in which Shapley value is used to realize the fairness of reward distribution of data providers. We consider the heterogeneity and privacy protection of participating individuals. The data providers’ resource allocation strategies are built as a Bayesian game model, which optimizes the local training strategy to realize the incentive effect on the data providers. Furthermore, we consider the effectiveness of the incentive mechanism, a privacy-preserving Bayesian game action strategy consensus algorithm (PPBG-AC) is proposed, which enables the data providers to realize Bayesian Nash equilibrium under a data trading platform based on blockchain. The comparison and analysis of the schemes reveal that the incentive mechanism presented in our paper assures benefit distribution fairness and resource allocation credibility. Simulation experiments and performance evaluations based on real datasets demonstrate the effectiveness of our incentive mechanism.

The transformation of old neighborhoods involves many important types of livelihood development projects, of which smart transformation is considered one of the most important tasks at present. The smart transformation of old neighborhoods provides an important means to promote sustainable development; however, enhancing the willingness of residents to participate is an important prerequisite for the smart transformation of old neighborhoods. Considering perceptive value acceptance theory and community ownership theory in the field of information management and sociology, we study the intention of residents in old communities to participate in intelligent transformation and its influence mechanisms. Our results show that willingness to participate in the smart renovation of old residential areas is positively affected by the perceived value of smart renovation and the sense of community attachment of residents. The sense of community plays an intermediary role in the relationship between perceived value and willingness to participate in smart renovation. At the same time, the perceived value of intelligent renovation of old residential areas and a sense of community have chain mediating effects between perceived usefulness, perceived enjoyment, perceived risk, perceived cost, and willingness to participate. This paper not only achieves theoretical expansion but also provides good support for accelerating the intelligent transformation of old communities in China.

基于联邦学习的智能边缘计算在物联网领域有广泛的应用前景.联邦学习是一种将数据存储在参与节点本地的分布式机器学习框架,可以有效保护智能边缘节点的数据隐私.现有的联邦学习通常将模型训练的中间参数上传至参数服务器实现模型聚合,此过程存在两方面问题:一是中间参数的隐私泄露,现有的隐私保护方案通常采用差分隐私给中间参数增加噪声,但过度加噪会降低聚合模型质量;另一方面,节点的自利性与完全自治化的训练过程可能导致恶意节点上传虚假参数或低质量模型,影响聚合过程与模型质量.基于此,本文将联邦学习中心化的参数服务器构建为去中心化的参数聚合链,利用区块链记录模型训练过程的中间参数作为证据,并激励协作节点进行模型参数验证,惩罚上传虚假参数或低质量模型的参与节点,以约束其自利性.此外,将模型质量作为评估依据,实现中间参数隐私噪声的动态调整以及自适应的模型聚合.原型搭建和仿真实验验证了模型的实用性,证实本模型不仅能增强联邦学习参与节点间的互信,而且能防止中间参数隐私泄露,从而实现隐私保护增强的可信联邦学习模型.

Federated learning is a distributed machine learning framework that enables distributed model training with local datasets, which can effectively protect the data privacy of workers (i.e., intelligent edge nodes). The majority of federated learning algorithms assume that the workers are trusted and voluntarily participate in the cooperative model training process. However, the situation in practical application is not consistent with this. There are many challenges such as worker selection schemes for participating workers, which hamper the widespread adoption of federated learning. The existing research about worker selection scheme focused on multi-weight subjective logic model to calculate reputation value and adopted contract theory to motivate workers, which may exist subjective judgmental factors and unfair profit distribution. To address above challenges, we calculate the reputation value by model quality parameters to evaluate the reliability of workers. Blockchain is designed to store historical reputation value that realized tamperresistance and non-repudiation. Numerical results indicate that the worker selection scheme can improve the accuracy of the model and accelerate the model convergence.

Blockchain-based product traceability systems are receiving increasing attention from both industry and academia. Existing systems make full use of the traceability and non-modification characteristics of blockchain technology and realize the openness and transparency of product traceability information in the entire supply chain. However, existing systems do not consider government regulation, cannot protect enterprise sensitive private data effectively, and have performance bottlenecks. To address these problems, this paper proposes a product traceability scheme based on the permissioned blockchain within a double-layer framework. We introduce the double-layer framework and describe its advantages in detail. We also describe the smart contracts (chain code) in the double-layer framework. Finally, we test the performance of the proposed scheme through simulation experiments. The simulation results demonstrate the performance of nodes in the main layer, which is very important for consumers to obtain product traceability information, is optimized.

The concept of open banking has been a powerful trigger for the revolution in the financial services industry. When financial institutions disclose application programming interfaces (APIs) to third-party providers (TPPs), the biggest system risks concern issues such as malicious attack, data leakage and tampering, privacy disclosure and more. API is a new communication path for information systems, but it could be misused and tampered. To address this, we conceptualize a blockchain-based data sharing scheme for open banking named OBBC, in which the API’s information can be saved in a blockchain, that no one can dominate it. We propose an API consensus mechanism aims to ensures that the open API can’t be maliciously tampered. Moreover, zero knowledge proof and Merkel tree structure are used to realize that users’ privacy protection. In particular, we give the framework of our scheme and compare with existing data sharing schemes. We further implement a software prototype on fabric framework with real-world dataset. Experiment results show the feasibility, usability and scalability of our proposed open banking system.

近年来,以比特币为代表的数字货币快速发展引发了金融业界和学界的广泛关注及讨论,比特币的算法信任、去中心化、匿名交易、全网交易、总量有限等特点使其具备潜在的避险能力.在宏观经济金融不确定性加剧的背景下,有必要对比特币是否具有避险能力及其特征进行研究.基于宏观经济金融不确定性的视角,本文使用事件分析法和DCC-GARCH模型考察了比特币在中长期和短期对于来自宏观经济和金融市场风险的避险能力.结果表明:(1)比特币短期对于宏观经济和金融市场都具有较强的避险属性;(2)比特币在中长期无论是均值信息传递层面还是波动信息传递层面都对金融市场不确定性表现出较为显著的避险功能,而对宏观经济不确定性仅在波动信息传递层面表现出避险效应;(3)比特币对金融市场的避险功能大小具有动态时变性,投机性的增强可能会削弱其避险性.

The success of DNN pruning has led to the development of energy-efficient inference accelerators that support pruned models with sparse weight and activation tensors. Because the memory layouts and dataflows in these architectures are optimized for the access patterns during inference, however, they do not efficiently support the emerging sparse training techniques. In this paper, we demonstrate (a) that accelerating sparse training requires a co-design approach where algorithms are adapted to suit the constraints of hardware, and (b) that hardware for sparse DNN training must tackle constraints that do not arise in inference accelerators. As proof of concept, we adapt a sparse training algorithm to be amenable to hardware acceleration; we then develop dataflow, data layout, and load-balancing techniques to accelerate it. The resulting system is a sparse DNN training accelerator that produces pruned models with the same accuracy as dense models without first training, then pruning, and finally retraining, a dense model. Compared to training the equivalent unpruned models using a state-of-the-art DNN accelerator without sparse training support, Procrustes consumes up to 3.26x less energy and offers up to 4x speedup across a range of models, while pruning weights by an order of magnitude and maintaining unpruned accuracy.

With the continuous update and iteration of Internet Technology, e-commerce develops rapidly under the support of national preferential policies. In view of the advantages of Harvard Analysis Framework, this paper conducts an in-depth analysis and research on the financial statements of JD based on it. It mainly describes how to analyze the financial data of JD by using the three parts of strategy analysis, accounting analysis and financial analysis in the framework of Harvard analysis, so as to make targeted analysis and forecast for the future development and prospect of JD. Finally, based on the problems encountered by JD in its development and the data obtained from the analysis of financial statements, the corresponding solutions are given.

跨境金融通信对于现代金融业务的开展极为重要.环球银行金融电信协会(SWIFT)是跨境金融通信服务的主要提供者.现阶段,报文传输是SWIFT系统的主要业务,确保报文传输安全、准确、高效,是SWIFT系统的重要目标.但现阶段基于中心架构思想的SWIFT系统安全风险突出,传输效率低,成本较高.基于许可链分布式共识机制,提出BCSWIFT系统,对现有的SWIFT系统进行优化.首先,将SWIFT系统的传输网络划分为主网络层和附加网络层;其次,提出了基于双层网络结构的共识算法;第三,介绍了BCSWIFT系统的报文交互和传输机制;第四,出于金融业务数据商业保密考虑,提出了一种面向BCSWIFT系统的隐私保护机制;第五,对BCSWIFT系统的安全性进行了分析.以优化SWIFT系统的报文传输业务为例,阐释了基于许可链的跨境金融通信的基本机理,为确保跨境支付、清算、结算的安全、高效、准确和低成本化运作提供了新的思路,也为区块链技术大规模商业应用提供了重要参照.

针对基于众包竞赛中欺诈者筛除机制的黄金标准数据方法、聚类算法的离群点检测算法K-means-算法和DBSCAN算法,依赖于事先给定的参数,不适合大规模数据集检测的问题,提出基于样本连通图的离群点检测算法.首先,给定参数并重复调用离群点检测算法,识别数据中的离群点和聚类;其次,计算每两个样本之间的连接次数和连接强度,在给定连接强度下界δ的情况下,根据样本的连接强度来构造样本之间的连通图;最后,根据样本之间的连通情况,对样本进行标记,把样本标记为聚类节点和离群点.实验结果表明,该算法在放宽参数设置范围的情况下,缩小了离群点个数波动范围,提升了离群点识别准确率,优于对比算法和经典的黄金标准数据方法.

The blocks in the blockchain are arranged in chronological and historical order, and the blockchain is incapable of modification through data encryption technology and consensus mechanism, which makes product traceability to be an important application scenario of blockchain. To choose product information traceability technology, not only the feasibility of the technology but also the market attributes of the product and the producer should be considered, which makes the permissioned chain replace the public chain as an important deployment method of product information traceability. In the existing research results, the research on the traceability license chain mainly focuses on mechanism design and framework construction, and the consensus algorithm applicable to product information traceability is rarely studied. In the process of technology of engineering practice, practical byzantine fault tolerance was chosen more in league chain as the consensus of traceability chain mechanism (such as Hyperledger), but with the increasing number of participating nodes of the traceability chain efficiency will be significantly reduced, and the delay time will be significantly improved, resulting in most of the project is still in the stage of experiment. Based on this, a traceability license chain consensus mechanism based on double-layer architecture (DLPCM) is proposed, and its security is analyzed. Participants are divided into two layers on the vertical dimension, and different consensus mechanisms are adopted at different levels according to different deployment modes of blockchain. Finally, the traceability information query mechanism under the consensus mechanism is introduced, an important reference for the development and design of traceability system based on license chain is provided.

Cyber-physics system has drawn widespread attention of academia,and the protection problems and protection measures it faces are also increasingly becoming the research focus in the field.By combing the current research results about the security issues of cyber-physics system and corresponding protective measures at home and abroad,it is found that the security protection measures based on the overall multi-level coordination and distributed architecture have become the current research direction,which is in line with the features of distributed architecture of blockchain technology.Based on the introduction of the distributed topology of blockchain and its information security features,this paper proposed the idea of security protection in which the blockchain technology is integrated with the cyber-physics system,proved the possibility of combining the two parts,and constructed BCCPS framework mechanism of integrating the two parts deeply.The specific construction of BCCPS framework at both the basic level and the integrated level was highlighted.Finally,the security of BCCPS framework was demonstrated from four aspects:confidentiality,integrity,availability and traceability of information security.This research provides a new idea for establishing a secure and robust cyber-physics system.

Under the strategy of "One Belt and One Road",the business cooperation is a complicated systematic project and the strategic choice of enterprises shows a clustering feature across the strategic ecosphere,where the stability of the cooperation between enterprises become an important factor that affects the whole strategic goal.An important feature that many projects have under the One Belt and One Road strategy is that both the cooperation with local civil / commercial subjects and the more involvement of local government are required.Existing researches focus on the overview and summary based on exploratory experience,lacking in-depth theoretical analysis that reveals enterprises' strategic choice in the process of cluster evolution of cooperation.Using evolutionary game theory,this paper analyzes the enterprise cooperation and opportunistic behavior in the process of government regulation.The research results show that under the condition of rational economic man hypothesis,enterprises and local governments will adopt opportunism behavior in the process of enterprise cooperation.The governments should set special regulatory bodies,which should adopt the strategy of dynamic support or penalties to promote the stable development of the regional economy.