基于Beta信誉模型的虚假Web服务QoS反馈滤除算法

Unfair web service QoS feedback filtering algorithm based on Beta reputation

针对由于Web服务推荐用户提交虚假QoS反馈而导致的QoS预测准确度下降问题,提出了一种基于Beta信誉模型的虚假QoS反馈滤除算法。该算法首先将若干个经过认证的中心用户作为初始可信用户集;然后,评估用户反馈数据与可信用户集反馈数据的偏离程度;最后,根据用户提交的偏离反馈次数对其信誉度进行评估,并将信誉度高于可信阈值的用户判定为可信用户,使可信用户集得到更新。通过循环执行以上过程,大部分虚假用户将被分离出系统。实验结果表明:该算法具有较强的虚假用户筛查能力,可有效提升QoS预测算法的抗攻击能力。

During the process of web services selection, some service recommenders may give feed- backs which are inconsistent with their real experience intentionally, and thus causes the deviation of prediction results. To resolve this problem, an unfair QoS feedback filtering algorithm based on Beta reputation is proposed. Firstly, several certified center users are obtained to initialize the trustworthy set. Then, the deviation between the target user＇s feedback and the average value of trustworthy set is evaluated. Finally, each userrs reputation is calculated based on how many deviated feedbacks have been provided. The users whose reputation exceeds the trustworthy threshold will be recognized as trustworthy users. After several iterations, a majority of unfair users are filtered out. Experimental results demonstrate that the proposed approach can accurately filter out the unfair users and improve the robustness of QoS prediction algorithms against unfair feedback attacks.