SocialTrust: Enabling long-term social cooperation in peer-to-peer services

Peer-to-peer(P2P) services heavily rely on users’ cooperation to achieve desired performance. However, most current P2P systems only encourage short-term and direct cooperation between peers. The lack of incentives for long term and indirect cooperation has severely limited the performance of P2P systems. On the other hand, recent measurements on large-scale networks show that peers’ behavior often demonstrates strong social patterns. In this paper, we design and implement a social P2P network, named SocialTrust, based on peers’ common interests. In SocialTrust, each peer tries to find a small number of friends and maintains long term social links with them. We also propose a distributed trust mechanism. The trust between two friends reflects their cooperation level and serves as the credit limit between them. A peer with higher trust can download data from its friends more efficiently. The trust can be propagated among friends to support indirect reciprocity. We formally prove that the proposed distributed trust mechanism is secure and can defend against various forms of attacks. By adding asmall number of long term social links to the existing P2P network, SocialTrust relaxes the constraint of direct incentive mechanisms and encourages peers to perform various forms of long-term cooperation. Both trace-driven simulation and real Internet experiments show that SocialTrust can significantly improve file availability and download performance of current P2P file sharing systems.     

Artificial intelligence control for trust-based detection of attackers in 5G social networks

This study introduces a comprehensive framework designed for detecting and mitigating fake and potentially threatening user communities within 5G social networks. Leveraging geo-location data, community trust dynamics, and AI-driven community detection algorithms, this framework aims to pinpoint users posing potential harm. Including an artificial control model facilitates the selection of suitable community detection algorithms, coupled with a trust-based strategy to effectively identify and filter potential attackers. A distinctive feature of this framework lies in its ability to consider attributes that prove challenging for malicious users to emulate, such as the established trust within the community, geographical location, and adaptability to diverse attack scenarios. To validate its efficacy, we illustrate the framework using synthetic social network data, demonstrating its ability to distinguish potential malicious users from trustworthy ones.     

融合用户社会地位和矩阵分解的推荐算法

随着社交网络服务的日益流行,社交网络平台为推荐算法提供了丰富的额外信息.假设朋友之间共享更多的共同偏好并且用户往往易于接受来自朋友的推荐,越来越多的推荐系统利用社交网络中用户之间的信任关系来改进传统推荐算法的性能.然而,现有基于社交网络推荐算法忽略了2个问题：1)在不同的领域中,用户信任不同的朋友;2)由于用户在不同的领域内具有不同的社会地位,因此,用户在不同的领域内受朋友的影响程度是不同的.首先利用整体的社交网络结构信息和用户的评分信息推导特定领域社交网络结构,然后利用PageRank算法计算用户在特定领域的社会地位,最后提出了一种融合用户社会地位信息的矩阵分解推荐算法.在真实数据集上的实验结果表明：融合用户地位信息的矩阵分解推荐算法的性能优于传统的基于社交网络推荐算法.     

Credibility of Social Network Sites for Political Information Among Politically Interested Internet Users

Scholars have confirmed that political candidates are increasingly turning to social network sites (SNS) to persuade voters to vote for them, and that these sites have become prominent sources of political information. But a fundamental question arises about the sustainability of social networks as a campaign tool: How much do users trust the information they find there? This study employed an online survey to examine the degree to which politically interested online users view SNS as credible. SNS were ranked the least credible among the nine traditional and online sources examined. Reliance on social networks proved the strongest predictor of SNS credibility.     

Characterizing Economic and Social Properties of Trust and Reputation Systems in P2P Environment

Considering the fact that P2P （Peer-to-Peer） systems are self-organized and autonomous, social-control mechanism （like trust and reputation） is essential to evaluate the trustworthiness of participating peers and to combat the selfish, dishonest and malicious peer behaviors. So, naturally, we advocate that P2P systems that gradually act as an important information infrastructure should be multi-disciplinary research topic, and reflect certain features of our society. So, from economic and social perspective, this paper designs the incentive-compatible reputation feedback scheme based on well-known economic model, and characterizes the social features of trust network in terms of efficiency and cost. Specifically, our framework has two distinctive purposes： first, from high-level perspective, we argue trust system is a special kind of social network, and an accurate characterization of the structural properties of the network can be of fundamental importance to understand the dynamics of the system. Thus, inspired by the concept of weighted small-world, this paper proposes new measurements to characterize the social properties of trust system, that is, high global and local efficiency, and low cost; then, from relative low-level perspective, we argue that reputation feedback is a special kind of information, and it is not free. So, based on economic model, VCG （Vickrey-Clarke-Grove）-like reputation remuneration mechanism is proposed to stimulate rational peers not only to provide reputation feedback, but truthfully offer feedback. Furthermore, considering that trust and reputation is subjective, we classify the trust into functional trust and referral trust, and extend the referral trust to include two factors： similarity and truthfulness, which can efficiently reduce the trust inference error. The preliminary simulation results show the benefits of our proposal and the emergence of certain social properties in trust network.     

Personalized Tag Recommendation Using Social Influence

Tag recommendation encourages users to add more tags in bridging the semantic gap between human concept and the features of media object,which provides a feasible solution for content-based multimedia information retrieval.In this paper,we study personalized tag recommendation in a popular online photo sharing site - Flickr.Social relationship information of users is collected to generate an online social network.From the perspective of network topology,we propose node topological potential to characterize user’s social influence.With this metric,we distinguish different social relations between users and find out those who really have influence on the target users.Tag recommendations are based on tagging history and the latent personalized preference learned from those who have most influence in user’s social network.We evaluate our method on large scale real-world data.The experimental results demonstrate that our method can outperform the non-personalized global co-occurrence method and other two state-of-the-art personalized approaches using social networks.We also analyze the further usage of our approach for the cold-start problem of tag recommendation.     

基于社会学理论的信任关系预测模型

随着社会网络的盛行,信任作为用户之间交互的基础,在信息共享、经验交流和社会舆论方面发挥着重要作用。然而,信任是一个复杂而抽象的概念,受多种因素影响,很难识别信任形成的诱因以及其形成机制。由于来自社会科学的社会学理论有助于解释社会现象,而社会网络反映了现实世界中用户之间的联系,因此,从社会学角度出发,通过研究社会等级理论和同质性理论获取信任关系的发展规律,进而构建信任关系预测模型。首先,对社会等级理论和同质性理论进行阐述,并验证了社会等级理论和同质性理论在社会网络中的存在;然后,分别针对社会等级理论和同质性理论对信任关系的影响提出社会等级正则化方法和同质性正则化方法;最后,利用非负矩阵的三维分解方法并结合社会等级理论和同质性理论实现对信任关系预测的建模,并提出 SocialTrust 模型用于信任关系预测。实验结果表明,相比于其他方法,该方法在信任关系预测方面具有较高的精度。     

Multi-criteria assessment of user trust in Social Reviewing Systems with subjective logic fusion

By now people’s opinions and actions are more and more strongly influenced by what is posted and shared on the various social networks. Thus, malicious users can purposely manipulate other users posting fake news/reviews. In order to face this challenge, modern online social networks are beginning to adopt tool for user trustworthiness assessment. Current assessment solutions mainly adopt multi-criteria frameworks for user trustworthiness assessment but fail at properly dealing with uncertainty and vagueness in computed/collected scores and aggregating them in a robust manner. In this paper, we propose a larger set of criteria than existing related works, and the use of subjective logic to represent and combine subjective and objective scores. Specifically, several of assessment criteria are introduced for verifying user trust from different point of views (usefulness and quality of user reviews, users’ influence/importance in terms of activities and centrality within the social network, time dependent crown consensus investigating aspect-based sentiments and opinions of reviews w.r.t. the majority), aiming at improving accuracy and precision in trust estimation. The available fusion operators in the literature of subjective logic have been compared so as to find the best one fitting the needs of trust estimation. The proposed solution has been implemented and evaluated against public Yelp data-sets so as to prove its effectiveness and efficiency w.r.t. existing related works within the literature.     

Privacy protection of online social network users,against attribute inference attacks,through the use of a set of exhaustive rules

Neural Computing and Applications - A malicious data miner can infer users’ private information in online social networks (OSNs) by data mining the users’ disclosed information. By...     

A novel trust management scheme based on Dempster–Shafer evidence theory for malicious nodes detection in wireless sensor networks

With the development of Internet technology, social network has become an important application in the network life. However, due to the rapid increase in the number of users, the influx of a variety of bad information is brought up as well as the existence of malicious users. Therefore, it is emergent to design a valid management scheme for user’s authentication to ensure the normal operation of social networks. Node trust evaluation is an effective method to deal with typical network attacks in wireless sensor networks. In order to solve the problem of quantification and uncertainty of trust, a novel trust management scheme based on Dempster–Shafer evidence theory for malicious nodes detection is proposed in this paper. Firstly, by taking into account spatiotemporal correlation of the data collected by sensor nodes in adjacent area, the trust degree can be estimated. Secondly, according to the D–S theory, the trust model is established to count the number of interactive behavior of trust, distrust or uncertainty, further to evaluate the direct trust value and indirect trust value. Then, a flexible synthesis method is adopted to calculate the overall trust to identify the malicious nodes. The simulation results show that the proposed scheme has obvious advantages over the traditional methods in the identification of malicious node and data fusion accuracy, and can obtain good scalability.

     

Strategies for predicting local trust based on trust propagation in social networks

Trust plays a critical role in determining social interactions in both online and offline networks, and reduces information overload, uncertainties and risk from unreliable users. In a social network, even if two users are not directly connected, one user can still trust the other user if there exists at least one path between the two users through friendship networks. This is the result of trust propagation based on the transitivity property of trust, which is “A trusts B and B trusts C, so A will trust C”. It is important to provide a trust inference model to find reliable trust paths from a source user to an unknown target user, and to systematically combine multiple trust paths leading to a target user. We propose strategies for estimating level of trust based on Reinforcement Learning, which is particularly well suited to predict a long-term goal (i.e. indirect trust value on long-distance user) with short-term reward (i.e. direct trust value between directly connected users). In other words, we compare and evaluate how the length of available trust paths and aggregation methods affects prediction accuracy and then propose the best strategy to maximize the prediction accuracy.     

TCR: a trustworthy and churn-resilient academic distribution and retrieval system in P2P networks

As the number of people using the internet has surged over the past few years, more and more people are choosing to share and retrieve information online. There are several decentralized retrieval applications that provide file-sharing platforms for exactly this purpose. However, these applications cannot guarantee churn resilience, trustworthiness, or low cost of retrieval. Therefore, in this paper, we present a system called trustworthy and churn-resilient academic distribution and retrieval system in P2P networks, or TCR, which: (1) ensures that information will not be centralized by central network administrators; (2) utilizes LSH to classify nodes with similar research topics into a local subnetwork, and applies routing algorithms with trust score equations to determine the next trustworthy node to forward the message, thus ensuring each node can accurately and efficiently find its trustworthy nodes within only a few hops; (3) provides a trustworthy management system that itself deals in trustworthiness, ensuring that even when there is a large proportion of malicious nodes, the system can still detect and punish misbehaving nodes; (4) guarantees that nodes can still retrieve the desired files even when in high-churn networks. We finally demonstrate that our TCR entails low message costs, provides high match rates, detects malicious nodes, and ensures churn resilience and search efficiency when compared to other P2P retrieval systems.

     

Self-nominating trust model based on hierarchical fuzzy systems for peer-to-peer networks

Security is a critical constraint for the expansion of Peer-to-Peer (P2P) networks. The autonomy, dynamic and distribution natures benefit both valid and malicious users and also lead that P2P networks are extremely susceptible to malicious users. Exploiting a reputation-based trust model is a feasible solution in such an open environment to build trust relationship among peers. While most of existing trust models focus on restraining the abuse and malicious attacks, intentions and sharing capabilities of peers are mostly ignored. In this paper, we present a self-nominating trust model based on hierarchical fuzzy systems to quantify the behaviors of peers. The reputation is defined based on eight factors, where three promising factors are provided by resource holders to demonstrate their desires, and four capability factors are recorded by requesters to identify the provider’s service capability. The approach degree based updating recommendation is deployed to aggregate the global trust metrics. Experimental results illustrate that our trust model effectively improves the efficiency and security of P2P systems.     

Resource recommendation in social annotation systems: A linear-weighted hybrid approach

Social annotation systems enable the organization of online resources with user-defined keywords. Collectively these annotations provide a rich information space in which users can discover resources, organize and share their finds, and connect to other users with similar interests. However, the size and complexity of these systems can lead to information overload and reduced utility for users. For these reasons, researchers have sought to apply the techniques of recommender systems to deliver personalized views of social annotation systems. To date, most efforts have concentrated on the problem of tag recommendation – personalized suggestions for possible annotations. Resource recommendation has not received the same systematic evaluation, in part because the task is inherently more complex. In this article, we provide a general formulation for the problem of resource recommendation in social annotation systems that captures these variants, and we evaluate two cases: basic resource recommendation and tag-specific resource recommendation. We also propose a linear-weighted hybrid framework for resource recommendation. Using six real-world datasets, we show that its integrative approach is essential for this recommendation task and provides the most adaptability given the varying data characteristics in different social annotation systems. We find that our algorithm is more effective than other more mathematically-complex techniques and has the additional advantages of flexibility and extensibility.     

User bias in online trust systems: aligning the system designers’ intentions with the users’ expectations

The advent of social networks opened a myriad opportunities for merging the social character of trust with the technical possibilities offered by the Internet and its availability as a mobile service. While most of the computational trust models aim to detect trustworthy entities, much less attention is paid to how these models are perceived by the users who are the core of the system. This paper delves into the workings of online trust systems under user bias and analyses the user behaviour through biases defined by Prospect theory. By performing empirical study on an existing system, we are able to demonstrate that there is a huge discrepancy between the aim of implementation of the online trust models and the users’ perception of those models. Understanding of this relation by the system designers can reduce complexity and improve the user experience and the system performance. The results imply that the tendency of the users to exhibit cognitive biases is not only the cause, but also the effect from the trust system design. These results and the analysis are then used to propose to the system designers a methodology for user bias identification and mitigation in the form of a Choice architecture for trust systems.     

一种基于反馈可信度的分布式P2P信任模型

开放、共享与匿名的Peer-to-Peer(简称P2P)网络已经取得了越来越多的应用,无中心对等的特性也吸引了越来越多的用户.但由于其网络中的节点不受约束,资源的共享是用户自愿的行为,因此节点间的信任很难通过传统的信任机制建立.一种可行的解决方案是借鉴人际网络中的信任关系,建立一种基于信誉的全局信任模型.已有的工作基本建立在信任度高的节点其反馈也更可信这个假设的基础上,将节点的反馈质量简单地等同于服务质量.针对这一问题,提出了一种基于节点反馈可信度的分布式P2P全局信任模型(简称FCTrust),用于量化和评估节点的可信程度,并给出了模型的数学表述和分布式实现方法.分析及仿真实验结果表明,FCTrust较已有的全局信任模型在遏制更广泛类型的恶意节点攻击的有效性、迭代计算的收敛性及消息成本上有较大提高.     

The power of comments: fostering social interactions in microblog networks

Today’s ubiquitous online social networks serve multiple purposes, including social communication (Facebook, Renren), and news dissemination (Twitter). But how does a social network’s design define its functionality? Answering this would need social network providers to take a proactive role in defining and guiding user behavior. In this paper, we first take a step to answer this question with a data-driven approach, through measurement and analysis of the Sina Weibo microblogging service. Often compared to Twitter because of its format,Weibo is interesting for our analysis because it serves as a social communication tool and a platform for news dissemination, too. While similar to Twitter in functionality, Weibo provides a distinguishing feature, comments, allowing users to form threaded conversations around a single tweet. Our study focuses on this feature, and how it contributes to interactions and improves social engagement.We use analysis of comment interactions to uncover their role in social interactivity, and use comment graphs to demonstrate the structure of Weibo users interactions. Finally, we present a case study that shows the impact of comments in malicious user detection, a key application on microblogging systems. That is, using properties of comments significantly improves the accuracy in both modeling and detection of malicious users.     

Expectations of privacy and trust: examining the views of IT professionals

The growth of interactive online lifestyles and social networks has arguably left IT users more exposed to privacy breaches. While governments continue to revise privacy legislation, the issue of online business relationships and privacy expectations remain contentious. Indeed, fewer studies have explored the expectations of users who willingly and knowingly engage in online activities that carry privacy risks. In this study, we examine the expectations and attitudes towards online privacy of a select group of 102 IT professionals. Using a qualitative survey, we show that these users have expectations of online privacy, particularly securing and protecting information from unknown third parties. Unfortunately, these expectations may go unsatisfied with third-party monitoring enabling information disclosure. In response, users argue that enhanced technical and complementary administrative measures should be actively pursued to improve privacy outcomes. The article builds further understanding of privacy expectations and trust behaviours, while exposing the importance of technical credibility from the online organisation and user perspectives.     

Twitter summarization with social-temporal context

Twitter is one of the most popular social media platforms for online users to create and share information. Tweets are short, informal, and large-scale, which makes it difficult for online users to find reliable and useful information, arising the problem of Twitter summarization. On the one hand, tweets are short and highly unstructured, which makes traditional document summarization methods difficult to handle Twitter data. On the other hand, Twitter provides rich social-temporal context beyond texts, bringing about new opportunities. In this paper, we investigate how to exploit social-temporal context for Twitter summarization. In particular, we provide a methodology to model temporal context globally and locally, and propose a novel unsupervised summarization framework with social-temporal context for Twitter data. To assess the proposed framework, we manually label a real-world Twitter dataset. Experimental results from the dataset demonstrate the importance of social-temporal context in Twitter summarization.     

RETENTION: A reactive trust-based mechanism to detect and punish malicious nodes in ad hoc grid environments

In ad hoc grid environments, resources are not always available since nodes can spontaneously connect and disconnect at any time. Thus, these environments demand the correct execution of tasks to guarantee good performance. However, there are malicious users that affect the normal operation of these grids. These users modify tasks results and even cheat security mechanisms. Therefore, to assure high performance in these grid computing scenarios, it is essential to use punishment procedures based on trust models. These solutions have been used in wireless ad hoc networks, but not in the context of ad hoc grid computing. Thus, in this paper, we first present an analysis of mathematical trust models in ad hoc grid scenarios, using different ways to treat detection information passed on by other nodes. Then, we provide a comparison and a performance evaluation of these models using a grid simulator platform. Besides that, we choose the most accurate trust model among the evaluated ones to propose RETENTION: a reactive trust-based mechanism to detect and punish malicious nodes in ad hoc grid environments. Simulation results demonstrate the effectiveness of the proposed approach in detecting and punishing up to 100% of malicious nodes without generating false-positives. The results can be a valuable tool for network designers in planning trust models in ad hoc grid network deployments.