基于人工免疫的比特币快捷交易异常检测模型

电子货币交易最重要的问题是双重花费（双花攻击）,比特币预防双花攻击的策略是等待六个确认块（约1 h）,难以适用于快捷支付领域,默认替代策略是等待交易信息传播到卖主的钱包,这无法有效地预防双花攻击。针对比特币快捷交易中双花攻击的检测问题,提出了一种基于人工免疫的比特币快捷交易异常检测模型。在每个传统比特币节点中加入免疫检测模块进行抗原提取,并利用检测器进行异常检测,在威胁控制中心动态演化检测器并分发免疫疫苗以便有效地进行防御。实验结果证明,此检测模型能够有效地检测并预防比特币快捷支付中的双花攻击。     

基于以太坊和动态定价的数据交易模式研究

为了解决现有数据交易模式中交易流程耗时较大且效率较低,信息泄露和公平支付问题,提出一种改进的数据交易模式,通过智能合约预置额外的约束条件,集成了数据交易和仲裁纠纷解决的功能,用于实现交易的公平自治性和交易时间控制,以规避数据交易过程中恶意交易行为。在此基础上,为实现所提出的数据交易模式中价格的动态平衡,基于经济建模方法和动态定价的公平合理性,设计一个自动平衡总供给和总需求的动态定价机制,依据购买需求和数据资源的市场供给进行价格动态调整。从模型的动态性对模型进行了论证,证明了交易价格和需求可以收敛。基于以太坊实验环境部署并执行该合约,并对该智能合约的各功能成本和安全性进行测试和分析。仿真实验结果表明,该改进交易模式在动态定价下能够以较低的执行成本进行数据交易,并且该智能合约存在较少代码漏洞,满足可行性和安全性要求。     

Predictive-Analysis-based Machine Learning Model for Fraud Detection with Boosting Classifiers

Fraud detection for credit/debit card, loan defaulters and similar types is achievable with the assistance of Machine Learning (ML) algorithms as they are well capable of learning from previous fraud trends or historical data and spot them in current or future transactions. Fraudulent cases are scant in the comparison of non-fraudulent observations, almost in all the datasets. In such cases detecting fraudulent transaction are quite difficult. The most effective way to prevent loan default is to identify non-performing loans as soon as possible. Machine learning algorithms are coming into sight as adept at handling such data with enough computing influence. In this paper, the rendering of different machine learning algorithms such as Decision Tree, Random Forest, linear regression, and Gradient Boosting method are compared for detection and prediction of fraud cases using loan fraudulent manifestations. Further model accuracy metric have been performed with confusion matrix and calculation of accuracy, precision, recall and F-1 score along with Receiver Operating Characteristic (ROC )curves.     

Energy trading scheme based on consortium blockchain and game theory

With the gradual opening of the electricity sales market, distributed energy trading is becoming an important research topic. However, it is not easy to design practical energy trading schemes in distributed scenario. In particular, known distributed energy trading schemes do not address the security of transaction data and the maximization of benefits among all the participants. In this paper, we propose a distributed energy trading scheme based on consortium blockchain and game theory. In our scheme, a peer-to-peer trading platform is constructed to realize direct transactions among all the participants by the property of decentralization in consortium blockchain. The direct transactions greatly reduce operating costs of energy trading, and at the same time, the security of transaction data can be obtained by the cryptographic techniques such as digital signatures and hash functions associated with the underlying blockchain. Moreover, we design an energy transaction matching mechanism by game theory in our scheme. In the matching mechanism, we construct a game model among all the participants and design an equilibrium solving algorithm, which are the key techniques to realize the maximization of benefits among all the participants in energy trading. The security analysis and experimental results show that our scheme can realize the best transaction price and quantity in the transaction matching and has high security in distributed energy transaction scenarios.     

基于无证书签密技术的NFC移动支付方案

针对现有的大部分NFC移动支付方案中存在的证书管理复杂、消费者隐私保护力度不大和运行效率不高等问题,结合无双线性对的无证书签密技术和匿名技术,提出了一个高效安全的NFC移动支付方案。该方案使用动态更新的匿名交易账户实现消费者匿名交易的同时实现了交易的不可链接性,商户作为消费者和移动支付服务提供商的通信桥梁,实现了消费者离线支付。分析结果表明,该方案在提供了高安全性交易和高质量的个人隐私保护的同时,实现了高效率的移动支付。     

面向比特币交易网络的拓扑结构可视探索方法

分析比特币交易网络有助于人们理解交易者在比特币交易中的交易模式.比特币交易网络的匿名性和其巨大的规模使得用户很难在分析前对整个交易网络产生大致的认知.提出了一种基于拓扑结构推荐的比特币交易网络可视分析方法.核心思想是为每个节点生成一个向量化表达,在用户交互的基础上,所提算法即可检测一系列相似的结构.案例分析证明了系统能够支持用户对比特币交易中的交易模式进行探索和分析.     

具有隐私保护的安全电子交易协议

电子交易的普及在给用户带来便利的同时,其在交易支付中所暴露出的隐私保护和安全性问题也受到不同程度的挑战。针对此问题,提出一个安全的电子交易协议。协议中,优化后的签密算法可保证交易的安全性;同时支付服务商具有去匿名性功能,可以在保护用户隐私的基础上进行追责。经性能分析,本协议在提高通信性能的基础上,满足消息的机密性和不可否认性、购买者的匿名性和可追踪性以及电子交易的公平性。     

A gradient boosting decision tree approach for insider trading identification: An empirical model evaluation of China stock market

Insider trading is a kind of criminal behavior in stock market by using nonpublic information. In recent years, it has become the major illegal activity in China’s stock market. In this study, a combination approach of GBDT (Gradient Boosting Decision Tree) and DE (Differential Evolution) is proposed to identify insider trading activities by using data of relevant indicators. First, insider trading samples occurred from year 2007 to 2017 and corresponding non-insider trading samples are collected. Next, the proposed method is trained by the GBDT, and initial parameters of the GBDT are optimized by the DE. Finally, out-of-samples are classified by the trained GBDT–DE model and its performances are evaluated. The experiment results show that our proposed method performed the best for insider trading identification under time window length of ninety days, indicating the relevant indicators under 90-days time window length are relatively more useful. Additionally, under all three time window lengths, relative importance result shows that several indicators are consistently crucial for insider trading identification. Furthermore, the proposed approach significantly outperforms other benchmark methods, demonstrating that it could be applied as an intelligent system to improve identification accuracy and efficiency for insider trading regulation in China stock market.     

基于排队博弈的最优比特币交易费支付策略

在比特币交易高峰期,为使交易尽快被打包进入区块,用户需要提高交易费以竞争有限的区块空间。针对用户如何自主选择合适交易费的问题,提出了最优的交易费支付策略。首先,结合排队博弈论将交易排队竞争上链的过程建模为一个带优先权的非抢占型排队模型;然后,分析交易费对交易耗时的影响,由此给出交易耗时与交易费之间的函数关系式,并推导出用户的纳什均衡支付策略。仿真结果表明,采用最优的支付策略可以有效降低用户的总花费（等待开销与交易费的加权和）。当系统高负荷时,与不支付交易费和按拥塞度线性增加交易费这两种策略相比,所提策略的用户总花费分别降低了97%和72%。由此可见,在保证交易被尽快处理的同时,所提支付策略可以有效减少交易费支出。     

基于排队博弈的最优比特币交易费支付策略

在比特币交易高峰期，为使交易尽快被打包进入区块，用户需要提高交易费以竞争有限的区块空间。针对用户如何自主选择合适交易费的问题，提出了最优的交易费支付策略。首先，结合排队博弈论将交易排队竞争上链的过程建模为一个带优先权的非抢占型排队模型；然后，分析交易费对交易耗时的影响，由此给出交易耗时与交易费之间的函数关系式，并推导出用户的纳什均衡支付策略。仿真结果表明，采用最优的支付策略可以有效降低用户的总花费（等待开销与交易费的加权和）。当系统高负荷时，与不支付交易费和按拥塞度线性增加交易费这两种策略相比，所提策略的用户总花费分别降低了97%和72%。由此可见，在保证交易被尽快处理的同时，所提支付策略可以有效减少交易费支出。     

基于银行账户亲密度网络推理的团伙预测研究

近年来,针对涉众型非法金融活动在资金交易规律的研究引起了研究者的高度关注。为解决利用银行交易数据进行异常账户犯罪团伙主动发现的问题,提出一种基于银行账户非对称亲密度网络的团伙预测方法。首先,建立银行账户交易通用网络模型,将时序交易数据嵌入网络结构中。然后,利用节点的直接和间接交易关系信息,提出一种账户非对称亲密度计算方法。最终,利用节点在亲密度网络上的非对称交互信息,得到节点的异常倾向性指标。在包含传销团伙的真实数据上的实验结果表明,基于亲密度网络的团伙预测方法能有效发现潜在传销人员。     

基于交易特征对以太网多类型非法账户的分析与预测

日益频繁的非法交易行为妨害以太坊安全交易,针对电子货币的匿名性使得非法交易行为难于跟踪分析问题。以太坊平台交易数据作为数据源,以被标记得非法账户和未标记的正常账户数据集作为训练集,利用交易数据的特征属性为构造基础,通过CatBoost算法对其中包含多种类型的非法账户进行整体预测。其过程通过T-SNE算法实现交易特征的降维可视化,采用多倍交叉验证,引入SHAP value因子判断特征影响的正负属性,所建立模型的预测效果准确率达到了94.29%,感受者曲线下面积（AUC）数值的评估度量达到了0.984 6。建议的方案能较为准确地预测以太坊交易平台上存在的非法行为,有效改善基于区块链的交易环境。     

Value-cell bar charts for visualizing large transaction data sets

One of the common problems businesses need to solve is how to use large volumes of sales histories, Web transactions, and other data to understand the behavior of their customers and increase their revenues. Bar charts are widely used for daily analysis, but only show highly aggregated data. Users often need to visualize detailed multidimensional information reflecting the health of their businesses. In this paper, we propose an innovative visualization solution based on the use of value cells within bar charts to represent business metrics. The value of a transaction can be discretized into one or multiple cells: high-value transactions are mapped to multiple value cells, whereas many small-value transactions are combined into one cell. With value-cell bar charts, users can 1) visualize transaction value distributions and correlations, 2) identify high-value transactions and outliers at a glance, and 3) instantly display values at the transaction record level. Value-cell bar charts have been applied with success to different sales and IT service usage applications, demonstrating the benefits of the technique over traditional charting techniques. A comparison with two variants of the well-known Tree map technique and our earlier work on pixel bar charts is also included.     

大规模交易事务的一种调度方法

为解决大规模交易中复杂事务密集访问引起的关键事务调度性能低下问题，文中通过研究交易事务的分类特点和结构特征，提出了一种基于虚拟截止期和时间戳排序的双级调度策略，通过分割长撮合事务和确定合理的步长因子，保证关键事务的优先调度，模拟和测试结果表明，在不产生事务延迟的条件下，交易事务的处理速率为1970事务／秒，平均响应时间为0．5ms，满足大规模电子交易的需要．     

Fair Trading Protocol with Offline Anonymous Credit Card Payment

Abstract

This paper proposes a fair trading protocol. The fair trading protocol provides an overall solution for a trading process with offline anonymous credit card payments.

With the exploding growth of electronic commerce on the Internet, the issue of fairness^1,2 is becoming increasingly more important. Fair exchange protocols have already been broadly used for applications such as electronic transactions,^3,4 electronic mails,^5,6and contract signing.⁷ Fairness is one of the critical issues in online transactions and related electronic payment systems. Many electronic payment systems have been proposed for providing different levels of security to financial transactions, such as iKP,⁸SET,⁹ NetBill,¹⁰ and NetCheque.¹¹ In a normal electronic commerce transaction, there is always a payer and a payee to exchange money for goods or services. At least one financial institution, normally a bank, should be present in the payment system. The financial institution plays the role of issuer for the payer and the role of acquirer for the payee. An electronic payment system must enable an honest payer to convince the payee of a legitimate payment and prevent a dishonest payer from using other unsuitable behavior. At the same time, some additional security requirements may be addressed based on the nature of trading processes and trust assumptions of the system. Payer, payee, and the financial institution have different interests and the trust between two parties should be as little as possible. In electronic commerce, the payment happens over an open network, such as the Internet, and the issue of fairness must be carefully addressed. There is no fairness for involved parties in the existing popular payment protocols. One target of this article is to address the fairness issue in the credit card payment process. In the existing credit card protocols, the financial institution that provides the credit card service plays the role of online authority and is actively involved in a payment. To avoid the involvement of financial institutions in normal transactions and to reduce running costs, some credit card-based schemes with offline financial authority have been proposed.¹² Another target of this article is to avoid the online financial institution for credit card service in normal transactions.     

基于第三方的安全电子支付模型的研究

探讨了电子商务支付系统的安全问题，分析了SET协议的基本结构和交易流程，根据电子商务的实际情况，对SET协议的流程做出适当的改进，提出了基于第三方支付中心的在线安全支付系统的解决方案。它将支付功能从商家系统剥离出来，作为独立的第三方支付中心，为各商家提供在线支付的支持。它优化了SET协议的模型结构，完善了交易流程，增强了交易的安全性。     

基于动机分析的区块链数字货币异常交易行为识别方法

当前区块链数字货币被众多恶意交易者利用,导致了“粉尘”注入、“空投”操作、勒索、骗局等一系列异常交易行为.因此,研究区块链数字货币异常交易行为的识别方法对于规范交易行为、保障网络空间安全具有重要意义.在众多区块链数字货币中,比特币市值超过所有区块链数字货币市值和的一半,具有高代表性.比特币系统的用户数量多、交易规模大、地址匿名化等特性,为异常交易行为的准确识别带来巨大挑战.鉴于任何比特币异常交易行为背后都存在着明确的动机,本文以分析交易动机为切入点,设计了一种新颖的比特币异常交易行为识别方法.具体地,我们以空投糖果和贪婪注资两类异常交易行为作为典型代表,分别设计了两类异常交易行为的判定规则,进而抽象出异常交易模式图.在此基础上,利用子图匹配技术设计实现了比特币异常交易行为的识别算法.为了评估本方法的效果,我们收集了近30个月的比特币历史交易数据,通过人工分析确定了异常交易行为的真值集.实验结果显示,空投糖果行为的识别召回率为85.71%、准确率为43.62%,贪婪注资行为的识别召回率为81.25%、准确率为54.32%.此外,我们重点分析展示了三个比特币异常交易行为的典型实例,通过真实案例进一步验证了本文所提方法的有效性.     

Speculative locking protocols to improve performance for distributed database systems

We have proposed speculative locking (SL) protocols to improve the performance of distributed database systems (DDBSs) by trading extra processing resources. In SL, a transaction releases the lock on the data object whenever it produces corresponding after-image during its execution. By accessing both before and after-images, the waiting transaction carries out speculative executions and retains one execution based on the termination (commit or abort) mode of the preceding transactions. By carrying out multiple executions for a transaction, SL increases parallelism without violating serializability criteria. Under the naive version of SL, the number of speculative executions of the transaction explodes with data contention. By exploiting the fact that a submitted transaction is more likely to commit than abort, we propose the SL variants that process transactions efficiently by significantly reducing the number of speculative executions. The simulation results indicate that even with manageable extra resources, these variants significantly improve the performance over two-phase locking in the DDBS environments where transactions spend longer time for processing and transaction-aborts occur frequently.     

结合静态语义和基于矩阵的异常事务识别方法

使用入侵检测找出数据库中异常事务是当前常用方法。但是，现今许多签字检测和非签字检测都是针对操作系统级而不是系统管理级，而且还不能保证对所有异常行为作出正确响应。为此给出一种新的异常事务识别方法。该方法使用静态语义分析读、写前及写后集合之间的关系来确定异常事务，使用基于矩阵的损失评估方法识别受此异常事务影响的数据客体。该方法由于避免读取数据库日志文件而减少了损失评估时间，但相关矩阵的存储需大量空间。     

SET协议认证机制的形式化分析

移动支付是移动电子商务的重要组成部分,而安全性成为移动支付的发展瓶颈,因此电子商务协议的安全性成为此问题的核心。为了解决上述问题,使用串空间模型的测试理论,对SET协议中用户和商家、商家和支付网关之间的认证性进行形式化分析,分析结果表明商家与支付网关之间的认证是安全的;用户和商家的认证性不满足安全需求,在支付交易流程中双方易受到攻击。