<p> </p><p>Millions of dollars change hands daily through online auction markets. Online trading communities like eBay and Amazon.com are emerging as increasingly important factors of the economy. Various Reputation systems are important components in such electronic markets. Existing evidence suggests that there are a number of problems with such systems. This paper presents an empirical exploration of reputation systems. Two studies of Tradera’s discussion forums are reported. The result of the first, pilot study suggests that both sellers and buyers are worried about getting a retaliatory negative feedback if they leave a negative feedback for an unsatisfactory transaction from their trading parties. Retaliation from the non-paying bidders seems to be the most severe threat and trouble for sellers. A set of negative feedbacks were then gathered from Tradera and data were manually analyzed in order to verify the results from the preliminary study. The results from the second study confirmed the result of the pilot study. A general evaluation of Tradera’s current reputation system is made based on the results of the second study. This paper aims to make a contribution to the literature on online reputation system by developing a typology of seller complaints about Tradera buyers and providing a tentative definition of retaliatory negative feedback based on the findings of both studies. Proposed solutions to the problems of non-payment and feedback retaliation are also presented.</p><p> </p>

No description available.

Dá-se o nome de sistemas de reputação a mecanismos em que membros de uma comunidade emitem avaliações sobre os demais e a partir destas se inferem quais dos membros podem ou não ser considerados confiáveis. Apresentamos, nesta dissertação de mestrado, um estudo sobre estes sistemas. Modela-se o problema de calcular reputações a partir de avaliações não-confiáveis como um problema de inferência estatística, que é então analisado com o uso de uma técnica conhecida como propagação de crenças, permitindo que obtenhamos estimativas. Em seguida, utilizamo-nos da relação existente entre problemas de inferência e mecânica estatística para realizar um estudo analítico mais profundo, por meio de uma generalização do método de cavidade. São traçados diagramas de fase, em que se observam regiões de parâmetros para as quais o problema torna-se mais difícil de resolver; esta análise nos dá alguma intuição sobre o problema, possibilitando que sejam propostas melhorias aos métodos existentes para tratá-lo. / It\'s given the name of reputation system to mechanisms in which members of a community issue each other ratings and from these it is inferred which can be trusted and which can\'t. We present, in this master\'s dissertation, a study on these systems. The problem of calculating reputations from unreliable ratings is modeled as one of statistical inference, and then analyzed with the use of a technique known as belief propagation, allowing us to obtain estimatives. Next, we use the existing relation between inference problems and statistical mechanics to motivate a deeper study, by means of a generalization of the cavity method. Phase diagrams are drawn, making possible to identify regions of parameters for which the problem is harder to solve; this analysis brings insight to the problem, allowing one to propose improvements to the methods available for it\'s treatment.

Millions of dollars change hands daily through online auction markets. Online trading communities like eBay and Amazon.com are emerging as increasingly important factors of the economy. Various Reputation systems are important components in such electronic markets. Existing evidence suggests that there are a number of problems with such systems. This paper presents an empirical exploration of reputation systems. Two studies of Tradera’s discussion forums are reported. The result of the first, pilot study suggests that both sellers and buyers are worried about getting a retaliatory negative feedback if they leave a negative feedback for an unsatisfactory transaction from their trading parties. Retaliation from the non-paying bidders seems to be the most severe threat and trouble for sellers. A set of negative feedbacks were then gathered from Tradera and data were manually analyzed in order to verify the results from the preliminary study. The results from the second study confirmed the result of the pilot study. A general evaluation of Tradera’s current reputation system is made based on the results of the second study. This paper aims to make a contribution to the literature on online reputation system by developing a typology of seller complaints about Tradera buyers and providing a tentative definition of retaliatory negative feedback based on the findings of both studies. Proposed solutions to the problems of non-payment and feedback retaliation are also presented.

Dá-se o nome de sistemas de reputação a mecanismos em que membros de uma comunidade emitem avaliações sobre os demais e a partir destas se inferem quais dos membros podem ou não ser considerados confiáveis. Apresentamos, nesta dissertação de mestrado, um estudo sobre estes sistemas. Modela-se o problema de calcular reputações a partir de avaliações não-confiáveis como um problema de inferência estatística, que é então analisado com o uso de uma técnica conhecida como propagação de crenças, permitindo que obtenhamos estimativas. Em seguida, utilizamo-nos da relação existente entre problemas de inferência e mecânica estatística para realizar um estudo analítico mais profundo, por meio de uma generalização do método de cavidade. São traçados diagramas de fase, em que se observam regiões de parâmetros para as quais o problema torna-se mais difícil de resolver; esta análise nos dá alguma intuição sobre o problema, possibilitando que sejam propostas melhorias aos métodos existentes para tratá-lo. / It\'s given the name of reputation system to mechanisms in which members of a community issue each other ratings and from these it is inferred which can be trusted and which can\'t. We present, in this master\'s dissertation, a study on these systems. The problem of calculating reputations from unreliable ratings is modeled as one of statistical inference, and then analyzed with the use of a technique known as belief propagation, allowing us to obtain estimatives. Next, we use the existing relation between inference problems and statistical mechanics to motivate a deeper study, by means of a generalization of the cavity method. Phase diagrams are drawn, making possible to identify regions of parameters for which the problem is harder to solve; this analysis brings insight to the problem, allowing one to propose improvements to the methods available for it\'s treatment.

This Diploma Thesis introduces the basic concepts of reputation and trust, reputation systems and problems of multi-contextual models of reputation. It also describes practical aspects of multi-contextual models in web environment. Described contextual models are then used for design and implementation of real web application.

Online reputation systems are certainly the most overlooked 'heroes' of today's social Web. While these mechanisms are a vital element of every online transaction, they have received less consideration than some of their more well-known cousins, such as recommender systems or social networks, whose success would often not have been possible and tenable without their discrete but active backing. It then follows that despite their value and importance, the implementation of current reputation mechanisms has mostly been the result of trial-and-error. Resting on an economic perspective, this thesis regroups three chapters whose frameworks and findings aim at helping mechanism designers and researchers understand key mechanisms at play and develop more efficient online reputation systems. The first chapter examines the optimal number of ratings a reputation mechanism must make publicly available within an online marketplace in order to minimize cheating and maximize Pareto efficiency. I develop a moral hazard stage game featuring fictitious players which has the compelling property to prevent reputation effects from disappearing in the long run. I show that the number of ratings displayed by a reputation system is a fundamental predictor of market efficiency, and that the latter number should be kept minimal in order to maximize social welfare in the market – especially for economies proposing interactions with a high profit margin. The second chapter studies how different classes of reporting behaviours commonly found online affect the reliability of a reputation mechanism. I develop an iterative stochastic approximation model which I use to construct a behavioural measure of efficiency, so-called 'reporting bias'. I demonstrate that reporting bias tends towards its maximum when raters comply with the reports left by their predecessors. Following this result, I recommend to keep the rating interface separated from the rest of the reputation system. I also find that fake ratings are particularly harmful when one type of behaviour is present in the economy and suggest to counterbalance sybil attacks by displaying pairs of contrasted ratings. Finally, I defend the use of the arithmetic mean against the median as a way to compute reputation scores. The third chapter analyses how 5-star rating scales can lead to the formation of bimodal distributions of ratings within online marketplaces. Using a 2-time period model featuring altruistic raters, I identify the existence of a 'blind spot' of unrated transactions whose magnitude increases in the cost of rating and decreases in the number of buyers inhabiting the economy. Developing an additional model featuring Bayesian agents suffering from confirmatory bias, I show that non-binary rating scales can leave space to ambiguity and possibly wrong posteriors, even in the long run. Overall, results of the chapter hint that fine-grained rating scales best suit signalling reputation systems while coarse-grained scales should be preferred for sanctioning mechanisms.

Submitted by Nara Lays Domingues Viana Oliveira (naradv) on 2015-08-06T19:22:26Z No. of bitstreams: 1 DanielBertoglioComputacao.pdf: 2836903 bytes, checksum: d32fdc80bc5cb27105db4d97c0231d7f (MD5) / Made available in DSpace on 2015-08-06T19:22:26Z (GMT). No. of bitstreams: 1 DanielBertoglioComputacao.pdf: 2836903 bytes, checksum: d32fdc80bc5cb27105db4d97c0231d7f (MD5) Previous issue date: 2011 / Nenhuma / Atualmente, a atribuição de novas tecnologias aliadas à computação distribuída tem crescido exponencialmente devido a necessidade cada vez mais imposta de otimização dos recursos computacionais. As redes P2P (Peer-to-Peer) são um exemplo de arquitetura de sistemas distribuídos onde os nós atuam tanto na função de clientes como na de servidores. A relação desses nós participantes apresenta questões relacionadas à confiança devido as comunicações que esses realizam, e uma vez que o comportamento dos nós é dinâmico, indicam-se problemas voltados a segurança. Dessa forma, um sistema de reputação e confiança é um meio de se controlar o funcionamento da rede e demais problemas através de métodos de recompensa e penalização. Analisando o contexto de aplicação, nota-se que utilizar um mecanismo de penalização para limitar largura de banda, como acontece tradicionalmente em sistemas P2P, não é uma alternativa viável para ambientes LAN, devido justamente aos recursos que esse tipo de rede detém como característica própria. Dentre diversas outras possibilidades, a limitação de acesso às informações sobre os arquivos compartilhados evidencia adequadamente uma maneira concisa e aplicável para tratar a penalização em redes locais. Este trabalho tem como objetivo então o desenvolvimento de um sistema de reputação para redes locais, denominado TrustLP2P. O TrustLP2P propõe um modelo que visa adequar os aspectos do ambiente de rede local ao mesmo tempo em que atribui conceitos baseados em outros sistemas de reputação existentes, fazendo uso de valores de reputação e confiança para que os nós possam classificar uns aos outros. Aliado a isso, mensurando através dos valores de reputação os participantes, o sistema também tem por finalidade recompensar ou penalizar os nós de acordo com seu comportamento. Um exemplo de aplicação para o TrustLP2P é o LP2P (Local Peer-to-Peer ), uma plataforma de comunicação para ambientes distribuídos voltada para o compartilhamento de arquivos, desenvolvida pelo projeto da linha de pesquisa de Redes de Computadores e Sistemas Distribuídos do PIPCA, Unisinos. Assim, o sistema proposto proporciona ao LP2P um controle adequado sobre as ações dos nós, através de aspectos consistentes que são descritos no seu modelo. / Currently, assign new technologies designed to distributed computing has grown exponentially due to the need for optimization of computing resources. The P2P (Peer-to-Peer) is an example of architecture of distributed systems where the nodes work both in the role of client as the server. The relationship of these nodes presents issues relating to the trust due the communications between them, and since the behavior of nodes is dynamic, security problems are indicated. Thus, a reputation and trust system is one way to control the operation of the network and other problems through methods of reward and punishment. Analyzing the application context, it is notable that use a penalty mechanism to limit bandwidth, as traditionally happens in P2P systems, it is not a viable alternative for LAN environments, due to the resources that this type of network has its own characteristic. Among several other possibilities, limiting access to information about the shared _les shows a concise and applicable manner to establish the penalty in local networks. This study aims to develop a reputation system for local networks, called TrustLP2P. The TrustLP2P proposes a model that adapts aspects of the local network environment at the sime time that related concepts based on other existing reputation systems, making use of reputation and trust values so that the nodes can classify each other. Allied to this, measuring the values of reputation through the participants, the system also aims to reward or penalize the nodes according to their behavior. An application for TrustLP2P is LP2P (Local Peer-to-Peer), a communication platform for distributed environments focused on the sharing of _les, developed by the research project of Computer Networks and Distributed Systems of PIPCA, Unisinos. Thus, the proposed system provides for LP2P an adequate control over the actions of the nodes, through consistent aspects that are described in their model.

In multi-hop wireless network (MWN), the mobile nodes relay others’ packets for enabling new applications and enhancing the network deployment and performance. However, the selfish nodes drop the packets because packet relay consumes their resources without benefits, and the malicious nodes drop the packets to launch Denial-of-Service attacks. Packet drop attacks adversely degrade the network fairness and performance in terms of throughput, delay, and packet delivery ratio. Moreover, due to the nature of wireless transmission and multi-hop packet relay, the attackers can analyze the network traffic in undetectable way to learn the users’ locations in number of hops and their communication activities causing a serious threat to the users’ privacy. In this thesis, we propose efficient security protocols for thwarting packet drop attacks and preserving users’ privacy in multi-hop wireless networks. First, we design a fair and efficient cooperation incentive protocol to stimulate the selfish nodes to relay others’ packets. The source and the destination nodes pay credits (or micropayment) to the intermediate nodes for relaying their packets. In addition to cooperation stimulation, the incentive protocol enforces fairness by rewarding credits to compensate the nodes for the consumed resources in relaying others’ packets. The protocol also discourages launching Resource-Exhaustion attacks by sending bogus packets to exhaust the intermediate nodes’ resources because the nodes pay for relaying their packets. For fair charging policy, both the source and the destination nodes are charged when the two nodes benefit from the communication. Since micropayment protocols have been originally proposed for web-based applications, we propose a practical payment model specifically designed for MWNs to consider the significant differences between web-based applications and cooperation stimulation. Although the non-repudiation property of the public-key cryptography is essential for securing the incentive protocol, the public-key cryptography requires too complicated computations and has a long signature tag. For efficient implementation, we use the public-key cryptography only for the first packet in a series and use the efficient hashing operations for the next packets, so that the overhead of the packet series converges to that of the hashing operations. Since a trusted party is not involved in the communication sessions, the nodes usually submit undeniable digital receipts (proofs of packet relay) to a centralized trusted party for updating their credit accounts. Instead of submitting large-size payment receipts, the nodes submit brief reports containing the alleged charges and rewards and store undeniable security evidences. The payment of the fair reports can be cleared with almost no processing overhead. For the cheating reports, the evidences are requested to identify and evict the cheating nodes. Since the cheating actions are exceptional, the proposed protocol can significantly reduce the required bandwidth and energy for submitting the payment data and clear the payment with almost no processing overhead while achieving the same security strength as the receipt-based protocols. Second, the payment reports are processed to extract financial information to reward the cooperative nodes, and contextual information such as the broken links to build up a trust system to measure the nodes’ packet-relay success ratios in terms of trust values. A node’s trust value is degraded whenever it does not relay a packet and improved whenever it does. A node is identified as malicious and excluded from the network once its trust value reaches to a threshold. Using trust system is necessary to keep track of the nodes’ long-term behaviors because the network packets may be dropped normally, e.g., due to mobility, or temporarily, e.g., due to network congestion, but the high frequency of packet drop is an obvious misbehavior. Then, we propose a trust-based and energy-aware routing protocol to route traffics through the highly trusted nodes having sufficient residual energy in order to establish stable routes and thus minimize the probability of route breakage. A node’s trust value is a real and live measurement to the node’s failure probability and mobility level, i.e., the low-mobility nodes having large hardware resources can perform packet relay more efficiently. In this way, the proposed protocol stimulates the nodes not only to cooperate but also to improve their packet-relay success ratio and tell the truth about their residual energy to improve their trust values and thus raise their chances to participate in future routes. Finally, we propose a privacy-preserving routing and incentive protocol for hybrid ad hoc wireless network. Micropayment is used to stimulate the nodes’ cooperation without submitting payment receipts. We only use the lightweight hashing and symmetric-key-cryptography operations to preserve the users’ privacy. The nodes’ pseudonyms are efficiently computed using hashing operations. Only trusted parties can link these pseudonyms to the real identities for charging and rewarding operations. Moreover, our protocol protects the location privacy of the anonymous source and destination nodes. Extensive analysis and simulations demonstrate that our protocols can secure the payment and trust calculation, preserve the users’ privacy with acceptable overhead, and precisely identify the malicious and the cheating nodes. Moreover, the simulation and measurement results demonstrate that our routing protocols can significantly improve route stability and thus the packet delivery ratio due to stimulating the selfish nodes’ cooperation, evicting the malicious nodes, and making informed decisions regarding route selection. In addition, the processing and submitting overheads of the payment-reports are incomparable with those of the receipts in the receipt-based incentive protocols. Our protocol also requires incomparable overhead to the signature-based protocols because the lightweight hashing operations dominate the nodes’ operations.

The proposed research is in the area of attribute-based authorization systems. We address two specific research problems in this area. First, evaluating authorization policies in multi-authority systems where there are multiple stakeholders in the disclosure of sensitive data. The research proposes to consider all the relevant policies related to authorization in real time upon the receipt of an access request and to resolve any differences that these individual policies may have in authorization. Second, to enable a lot of entities to participate in the authorization process by asserting attributes on behalf of the principal accessing resources. Since it is required that these asserted attributes be trusted by the authorization system, it is necessary that these entities are themselves trusted by the authorization system. Two frameworks are proposed to address these issues. In the first contribution a dynamic authorization system is proposed which provides conflict detection and resolution among applicable policies in a multi-authority system. The authorization system is dynamic in nature and considers the context of an access request to adapt its policy selection, execution and conflict handling based on the access environment. Efficient indexing techniques are used to increase the speed of authorization policy loading and evaluation. In the second contribution, we propose a framework for service providers to evaluate trust in entities asserting on behalf of service users in real time upon receipt of an access request. This trust evaluation is done based on a reputation system model, which is designed to protect itself against known attacks on reputation systems.