An effective early fraud detection method for online auctions

While online auctions continue to increase, so does the incidence of online auction fraud. To avoid discovery, fraudsters often disguise themselves as honest members by imitating normal trading behaviors. Therefore, maintaining vigilance is not sufficient to prevent fraud. Participants in online auctions need a more proactive approach to protect their profits, such as an early fraud detection system. In practice, both accuracy and timeliness are equally important when designing an effective detection system. An instant but incorrect message to the users is not acceptable. However, a lengthy detection procedure is also unsatisfactory in assisting traders to place timely bids. The detection result would be more helpful if it can report potential fraudsters as early as possible. This study proposes a new early fraud detection method that considers accuracy and timeliness simultaneously. To determine the most appropriate attributes that distinguish between normal traders and fraudsters, a modified wrapper procedure is developed to select a subset of attributes from a large candidate attribute pool. Using these attributes, a complement phased modeling procedure is then proposed to extract the features of the latest part of traders’ transaction histories, reducing the time and resources needed for modeling and data collection. An early fraud detection model can be obtained by constructing decision trees or by instance-based learning. Our experimental results show that the performance of the selected attributes is superior to other attribute sets, while the hybrid complement phased models markedly improve the accuracy of fraud detection.     

CAT-RFE:点击欺诈的集成检测框架

点击欺诈是近年来最常见的网络犯罪手段之一,互联网广告行业每年都会因点击欺诈而遭受巨大损失。为了能够在海量点击中有效地检测欺诈点击,构建了多种充分结合广告点击与时间属性关系的特征,并提出了一种点击欺诈检测的集成学习框架——CAT-RFE集成学习框架。CAT-RFE集成学习框架包含3个部分:基分类器、递归特征消除(RFE,recursive feature elimination)和voting集成学习。其中,将适用于类别特征的梯度提升模型——CatBoost(categorical boosting)作为基分类器;RFE是基于贪心策略的特征选择方法,可在多组特征中选出较好的特征组合;Voting集成学习是采用投票的方式将多个基分类器的结果进行组合的学习方法。该框架通过CatBoost和RFE在特征空间中获取多组较优的特征组合,再在这些特征组合下的训练结果通过voting进行集成,获得集成的点击欺诈检测结果。该框架采用了相同的基分类器和集成学习方法,不仅克服了差异较大的分类器相互制约而导致集成结果不理想的问题,也克服了RFE在选择特征时容易陷入局部最优解的问题,具备更好的检测能力。在实际互联网点击欺诈数据集上的性能评估和对比实验结果显示,CAT-RFE集成学习框架的点击欺诈检测能力超过了CatBoost模型、CatBoost和RFE组合的模型以及其他机器学习模型,证明该框架具备良好的竞争力。该框架为互联网广告点击欺诈检测提供一种可行的解决方案。     

A scalable architecture for concurrent online auctions

Online auction systems are characterised by a number of functional and performance management requirements, caused by the potentially very large numbers of distributed concurrent bidders, as well as by the auction rules. Such systems are typically implemented as three tier, thread‐based architectures, whose performance does not scale up well with an increase in the number of concurrent bidders. Nor such systems can take advantage of new Cloud based environments. In this paper, we propose an architectural framework for online auctions developed on top of a soft real‐time platform (Open Telecom Platform) using a concurrent language (Erlang) and an embedded Web server (Yaws). The proposed framework can scale up to hundreds of thousands of concurrent users while its performance can benefit from multicore and symmetric multiprocessing computer architectures. We demonstrate the capabilities of the framework by developing prototypes for two auction types known as ‘unique bid’ and ‘penny’, analyse their performance characteristics and compare them with that of existing auction systems. Copyright © 2013 John Wiley & Sons, Ltd.     

Real-time detection of shill bidding in online auctions: A literature review

Online auctions have become an increasingly popular and convenient way for conducting ecommerce transactions on the Web. However, the rapid surge of users participating in online auctions has led to auction fraud. Among the types of auction fraud, the most prominent is Shill bidding. Shill bidding is intentionally fake bidding by a seller on his/her own auction to inflate the final price. This can be accomplished either by the seller himself/herself or by someone colluding with the seller to place fake bids on his/her behalf. Therefore, it is difficult to manually investigate the large amount of auctions and bidders for shill bidding activities. Detecting shill bidding in real-time is the most effective way to reduce the loss result of the auction fraud. Researchers have proposed multiple approaches and experimented to control the losses incurred due to shill bidding. This paper investigates the real-time detection techniques of shill bidding. It also provides a brief overview of major work that has been conducted in shill bidding detection including both offline and real-time approaches. Furthermore, this paper identifies research gaps in the detection and prevention of shill bidding behaviours. It also provides future research issues and challenges to detect shill bidding in real-time.     

Incremental collusive fraud detection in large-scale online auction networks

The Journal of Supercomputing - An online auction network (OAN) is a community of users who buy or sell items through an auction site. Along with the growing popularity of auction sites, concerns...     

A novel optimization framework for salient object detection

Visual saliency aims to locate the noticeable regions or objects in an image. In this paper, a coarse-to-fine measure is developed to model visual saliency. In the proposed approach, we firstly use the contrast and center bias to generate an initial prior map. Then, we weight the initial prior map with boundary contrast to obtain the coarse saliency map. Finally, a novel optimization framework that combines the coarse saliency map, the boundary contrast and the smoothness prior is introduced with the intention of refining the map. Experiments on three public datasets demonstrate the effectiveness of the proposed method.     

A novel edge-oriented framework for saliency detection enhancement

Mixed visual scenes and cluttered background commonly exist in natural images, which forms a challenge for saliency detection. In dealing with complex images, there are two kinds of deficiencies in the existing saliency detection methods: ambiguous object boundaries and fragmented salient regions. To address these two limitations, we propose a novel edge-oriented framework to improve the performance of existing salient detection methods. Our framework is based on two interesting insights: 1) human eyes are sensitive to the edges between foreground and background even there is hardly any difference in terms of saliency, 2) Guided by semantic integrity, human eyes tend to view a visual scene as several objects, rather than pixels or superpixels. The proposed framework consists of the following three parts. First, an edge probability map is extracted from an input image. Second, the edge-based over-segmentation is obtained by sharpening the edge probability map, which is ultilized to generate edge-regions using an edge-strength based hierarchical merge model. Finally, based on the prior saliency map generated by existing methods, the framework assigns each edge-region with a saliency value. Based on four publically available datasets, the experiments demonstrate that the proposed framework can significantly improve the detection results of existing saliency detection models, which is also superior to other state-of-the-art methods.     

A novel online boosting algorithm for automatic anatomy detection

This paper presents a novel online learning method for automatically detecting anatomic structures in medical images. Conventional off-line learning methods require collecting a complete set of representative samples prior to training a detector. Once the detector is trained, its performance is fixed. To improve the performance, the detector must be completely retrained, demanding the maintenance of historical training samples. Our proposed online approach eliminates the need for storing historical training samples and is capable of continually improving performance with new samples. We evaluate our approach with three distinct thoracic structures, demonstrating that our approach yields performance competitive with the off-line approach. Furthermore, we investigate the properties of our proposed method in comparison with an online learning method suggested by Grabner and Bischof (IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2006, vol. 1, pp. 260–267, 2006), which is the state of the art, indicating that our proposed method runs faster, offers more stability, improves handling of “catastrophic forgetting”, and simultaneously achieves a satisfactory level of adaptability. The enhanced performance is attributed to our novel online learning structure coupled with more accurate weaker learners based on histograms.     

Incremental learning framework for real‐world fraud detection environment

For detecting malicious bidding activities in e‐auctions, this study develops a chunk‐based incremental learning framework that can operate in real‐world auction settings. The self‐adaptive framework first classifies incoming bidder chunks to counter fraud in each auction and take necessary actions. The fraud classifier is then adjusted with confident bidders' labels validated via bidder verification and one‐class classification. Based on real fraud data produced from commercial auctions, we conduct an extensive experimental study wherein the classifier is adapted incrementally using only relevant bidding data while evaluating the subsequent adjusted models' detection and misclassification rates. We also compare our classifier with static learning and learning without data relevancy.     

Contrast effects in online auctions

Prior research has shown online auction features can serve as information cues and affect consumers’ willingness-to-pay. We argue that auctions are not only affected by their information cues but also by contrasting, peripheral information cues from adjacent auction listings. Applying contrast effects theory, we examined the moderating effects of time urgency and persuasion intent on the processing of contrasting peripheral information from adjacent auctions. Using two controlled experiments and an empirical field study, we showed that time urgency experienced by bidders in online auctions resulted in increased heuristic processing of contrasting information from adjacent auction listings. Under time pressure, bidders were more likely to be affected by this contrasting peripheral information. We also found that bidders will discount contrasting peripheral information if they perceive salient persuasion intents in advertising presented by the auctioneers. The resulting contrast effects ultimately lead to changes in willingness-to-pay and underscore the importance of peripheral information from adjacent auctions in impacting auction outcomes.     

A novel deep learning framework for copy-moveforgery detection in images

Multimedia Tools and Applications - In this era of technology, digital images turn out to be ubiquitous in a contemporary society and they can be generated and manipulated by a wide variety of...     

Secure authentication in motion: A novel online payment framework for drive-thru Internet

The security and privacy issues have been well investigated in typical vehicle ad hoc networks. However, considering the drive-thru Internet properties, in particular for a secure and in-motion payment services case, merely implementing the existing online payment schemes may be either infeasible or inefficient. In this paper, we propose an advanced online payment framework, which integrates three main features, including the novel pairing-free certificateless encryption, signature and semi-honest RSU-aided verification, and the CA-aided tracking and batch auditing, and providing following properties independently, e.g., achieving a higher trust level and supporting primary security services, introducing a semi-honest RSU to indicate more practicality, and optimizing the verifying and auditing efficiency for a large number of authentication requests case. Performance evaluations such as security analysis, efficiency analysis, and simulation evaluation show the security and feasibility of the proposed framework.     

A novel intrusion detection framework for wireless sensor networks

Vehicle cloud is a new idea that uses the benefits of wireless sensor networks (WSNs) and the concept of cloud computing to provide better services to the community. It is important to secure a sensor network to achieve better performance of the vehicle cloud. Wireless sensor networks are a soft target for intruders or adversaries to launch lethal attacks in its present configuration. In this paper, a novel intrusion detection framework is proposed for securing wireless sensor networks from routing attacks. The proposed system works in a distributed environment to detect intrusions by collaborating with the neighboring nodes. It works in two modes: online prevention allows safeguarding from those abnormal nodes that are already declared as malicious while offline detection finds those nodes that are being compromised by an adversary during the next epoch of time. Simulation results show that the proposed specification-based detection scheme performs extremely well and achieves high intrusion detection rate and low false positive rate.     

A two-stage framework for UML specification matching

Context

Specification matching techniques are crucial for effective retrieval processes. Despite the prevalence for object-oriented methodologies, little attention has been given to Unified Modeling Language (UML) for matching.

Objective

This paper presents a two-stage framework for matching two UML specifications and quantifying the results based on the systematic integration of their structural and behavioral similarities in order to identify the candidate component set for reuse.

Method

The first stage in the framework is an evaluation of the similarities between UML class diagrams using the Structure-Mapping Engine (SME), a simulation of the analogical reasoning approach known as the structure-mapping theory. The second stage, performed on the components identified in the first stage, is based on a graph-similarity scoring algorithm in which UML class diagrams and sequence diagrams are transformed into an SME representation and a Message-Object-Order Graph (MOOG). The effectiveness of the proposed framework was evaluated using a case study.

Results

The experimental results showed a reduction in potential mismatches and an overall high precision and recall.

Conclusion

It is concluded that the two-stage framework is capable of performing more precise matching compared to those of other single-stage matching frameworks. Moreover, the two-stage framework could be utilized within a reuse process, bypassing the need for extra information for retrieval of the components described by UML.     

A two-stage framework for cross-domain sentiment classification

Supervised sentiment classification systems are typically domain-specific, and the performance decreases sharply when transferred from one domain to another domain. Building these systems involves annotating a large amount of data for every domain, which needs much human labor. So, a reasonable way is to utilize labeled data in one existed (or called source) domain for sentiment classification in target domain. To address this problem, we propose a two-stage framework for cross-domain sentiment classification. At the “building a bridge” stage, we build a bridge between the source domain and the target domain to get some most confidently labeled documents in the target domain; at the “following the structure” stage, we exploit the intrinsic structure, revealed by these most confidently labeled documents, to label the target-domain data. The experimental results indicate that the proposed approach could improve the performance of cross-domain sentiment classification dramatically.     

Data driven design for online industrial auctions

Annals of Mathematics and Artificial Intelligence - Designing auction parameters for online industrial auctions is a complex problem due to highly heterogeneous items. Currently, online auctioneers...     

Antecedents of trust in online auctions

Customer loyalty or repeat purchasing is critical to the online auction sellers’ survival and success. Previous research has established that online repeat purchase intentions are the product of buyer assessments of trust in the online seller. Previous research has also affirmed the importance of justice perceptions in engendering trust. These perspectives, however, have been examined independently by IS and management researchers. By integrating these two perspectives, a richer understanding of buyers’ underlying beliefs and subsequent repeat purchase intentions can be gained. In the research model, bidding justice is proposed as a formative second-order construct driven by distributive justice, procedural justice, interpersonal justice, and informational justice. Bidding justice is hypothesized to positively affect trust in the community of sellers, which in turn is hypothesized to positively affect repeat purchase intentions. Data collected from 412 buyers in Yahoo-Kimo’s online auction marketplace provide support for the proposed model. The study shows that trust is a significant positive predictor of buyers’ intentions to repeat purchase. The study also shows that the four dimensions of justice are important components of bidding justice, which in turn has a strong positive effect on trust in the community of sellers. Implications for theory and practice and suggestions for future research are discussed.