Numerous complex systems such as rating systems are highly affected by a small number of spamming attackers. How to design a fast and effective ranking method under the threat of spamming attacks is significant in practice. In this paper, we extract the user’s rating characteristics from personal historical ratings to determine whether the user is normal. It is discovered that reliable users have little bias and their rating scores follow the pattern of peak distribution. On the opposite, malicious users usually have biased ratings and their rating scores scarcely follow a known patterns. A new reputation ranking method IOR (Iterative Optimization Ranking) is proposed based on user rating deviation and rating characteristics. The experimental results on three real datasets show that this method is more efficient than existing states of art methods. This new fundamental idea can be contributed to a new way to solve spammer attacking problem. It can also be applied in large and sparse bipartite rating networks in a short time.

诸如垃圾邮件评级系统之类的众多复杂系统受到少量垃圾邮件攻击者的高度影响。在垃圾邮件攻击威胁下，如何设计一种快速有效的排名方法在实践中具有重要意义。在本文中，我们从个人历史评分中提取用户的评分特征，以确定用户是否正常。发现可靠的用户几乎没有偏见，并且他们的评分分数遵循峰值分布的模式。相反，恶意用户通常具有偏颇的评分，其评分分数几乎没有遵循已知的模式。基于用户评分偏差和评分特征，提出了一种新的信誉排名方法IOR（迭代优化排名）。在三个真实数据集上的实验结果表明，该方法比现有技术水平的方法效率更高。这个新的基本思想可以为解决垃圾邮件发送者攻击问题的新方法做出贡献。它也可以在短时间内应用于大型和稀疏的两方评级网络。