主题相似度与链接权重相结合的垃圾网页排序检测

针对因Web中存在由正常网页指向垃圾网页的链接,导致排序算法(Anti-TrustRank等)检测性能降低的问题,提出了一种主题相似度和链接权重相结合,共同调节网页非信任值传播的排序算法,即主题链接非信任排序(TLDR)。首先,运用隐含狄利克雷分配(LDA)模型得到所有网页的主题分布,并计算相互链接网页间的主题相似度;其次,根据Web图计算链接权重,并与主题相似度结合,得到主题链接权重矩阵;然后,利用主题链接权重调节非信任值传播,改进Anti-TrustRank和加权非信任值排序(WATR)算法,使网页得到更合理的非信任值;最后,将所有网页的非信任值进行排序,通过划分阈值检测出垃圾网页。在数据集WEBSPAM-UK2007上进行的实验结果表明,与Anti-TrustRank和WATR相比,TLDR的SpamFactor分别提高了45%和23.7%,F1-measure(阈值取600)分别提高了3.4个百分点和0.5个百分点, spam比例(前三个桶)分别提高了15个百分点和10个百分点。因此,主题与链接权重相结合的TLDR算法能有效提高垃圾网页检测性能。     

Link-based web spam detection using weight properties

Link spam is created with the intention of boosting one target’s rank in exchange of business profit. This unethical way of deceiving Web search engines is known as Web spam. Since then many anti-link spam detection techniques have constantly being proposed. Web spam detection is a crucial task due to its devastation towards Web search engines and global cost of billion dollars annually. In this paper, we proposed a novel technique by incorporating weight properties to enhance the Web spam detection algorithms. Weight properties can be defined as the influences of one Web node towards another Web node. We modified existing Web spam detection algorithms with our novel technique to evaluate the performances on a large public Web spam dataset – WEBSPAM-UK2007. The overall performance have shown that the modified algorithms outperform the benchmark algorithms up to 30.5 % improvement at host level and 6.11 % improvement at page level.     

基于Bagging-SVM集成分类器的网页作弊检测

网页作弊不仅造成信息检索质量下降,而且给互联网的安全也带来了极大的挑战.提出了一种基于Bag-ging-SVM集成分类器的网页作弊检测方法.在预处理阶段,首先采用K-means方法解决数据集的不平衡问题,然后采用CFS特征选择方法筛选出最优特征子集,最后对特征子集进行信息熵离散化处理.在分类器训练阶段,通过Bagging方法构建多个训练集并分别对每个训练集进行SVM学习来产生弱分类器.在检测阶段,通过多个弱分类器投票决定测试样本所属类别.在数据集WEBSPAM-UK2006上的实验结果表明,在使用特征数量较少的情况下,本检测方法可以获得非常好的检测效果.     

基于遗传规划集成学习的网络作弊检测

网络作弊检测是搜索引擎的重要挑战之一,该文提出基于遗传规划的集成学习方法 (简记为GPENL)来检测网络作弊。该方法首先通过欠抽样技术从原训练集中抽样得到t个不同的训练集;然后使用c个不同的分类算法对t个训练集进行训练得到t*c个基分类器;最后利用遗传规划得到t*c个基分类器的集成方式。新方法不仅将欠抽样技术和集成学习融合起来提高非平衡数据集的分类性能,还能方便地集成不同类型的基分类器。在WEBSPAM-UK2006数据集上所做的实验表明无论是同态集成还是异态集成,GPENL均能提高分类的性能,且异态集成比同态集成更加有效;GPENL比AdaBoost、Bagging、RandomForest、多数投票集成、EDKC算法和基于Prediction Spamicity的方法取得更高的F-度量值。     

Combating Web spam through trust–distrust propagation with confidence

Semi-automatic anti-spam algorithms propagate either trust through links from a set of good seed pages or distrust through inverse-links from a set of bad seed pages to the entire Web. It has been mentioned that a combined usage of both trust and distrust propagations can lead to better results. However, little work has been known to realize this insight successfully. In this paper, we view that each Web page has both a trustworthy side and an untrustworthy side, and propose to assign two scores for each Web page to denote its trustworthy side and untrustworthy side, respectively. We then propose the Good-Bad Rank (GBR) algorithm for propagating trust and distrust simultaneously from both directions. In GBR, the propagation of a page’s trust/distrust is decided by its probability of being trust/distrust. GBR takes advantages from both trust and distrust propagations, thus is more powerful than propagating only trust or distrust. Experimental results show that GBR outperforms other typical link-based anti-spam algorithms that propagates only trust or distrust. GBR achieves comparable performance than another algorithm that propagates both trust and distrust, TDR, but is much more efficient than TDR.     

Graph regularization methods for Web spam detection

We present an algorithm, witch, that learns to detect spam hosts or pages on the Web. Unlike most other approaches, it simultaneously exploits the structure of the Web graph as well as page contents and features. The method is efficient, scalable, and provides state-of-the-art accuracy on a standard Web spam benchmark.     

基于随机森林和欠采样集成的垃圾网页检测

为解决垃圾网页检测过程中的不平衡分类和"维数灾难"问题,提出一种基于随机森林(RF)和欠采样集成的二元分类器算法。首先使用欠采样技术将训练样本集大类抽样成多个子样本集,再将其分别与小类样本集合并构成多个平衡的子训练样本集;然后基于各个子训练样本集训练出多个随机森林分类器;最后用多个随机森林分类器对测试样本集进行分类,采用投票法确定测试样本的最终所属类别。在WEBSPAM UK-2006数据集上的实验表明,该集成分类器算法应用于垃圾网页检测比随机森林算法及其Bagging和Adaboost集成分类器算法效果更好,准确率、F1测度、ROC曲线下面积(AUC)等指标提高至少14%,13%和11%。与Web spam challenge 2007 优胜团队的竞赛结果相比,该集成分类器算法在F1测度上提高至少1%,在AUC上达到最优结果。     

A novel ensemble decision tree based on under-sampling and clonal selection for web spam detection

Currently, web spamming is a serious problem for search engines. It not only degrades the quality of search results by intentionally boosting undesirable web pages to users, but also causes the search engine to waste a significant amount of computational and storage resources in manipulating useless information. In this paper, we present a novel ensemble classifier for web spam detection which combines the clonal selection algorithm for feature selection and under-sampling for data balancing. This web spam detection system is called USCS. The USCS ensemble classifiers can automatically sample and select sub-classifiers. First, the system will convert the imbalanced training dataset into several balanced datasets using the under-sampling method. Second, the system will automatically select several optimal feature subsets for each sub-classifier using a customized clonal selection algorithm. Third, the system will build several C4.5 decision tree sub-classifiers from these balanced datasets based on its specified features. Finally, these sub-classifiers will be used to construct an ensemble decision tree classifier which will be applied to classify the examples in the testing data. Experiments on WEBSPAM-UK2006 dataset on the web spam problem show that our proposed approach, the USCS ensemble web spam classifier, contributes significant classification performance compared to several baseline systems and state-of-the-art approaches.     

Image spam analysis and detection

Image spam is unsolicited bulk email, where the message is embedded in an image. Spammers use such images to evade text-based filters. In this research, we analyze and compare two methods for detecting spam images. First, we consider principal component analysis (PCA), where we determine eigenvectors corresponding to a set of spam images and compute scores by projecting images onto the resulting eigenspace. The second approach focuses on the extraction of a broad set of image features and selection of an optimal subset using support vector machines (SVM). Both of these detection strategies provide high accuracy with low computational complexity. Further, we develop a new spam image dataset that cannot be detected using our PCA or SVM approach. This new dataset should prove valuable for improving image spam detection capabilities.     

一种面向微博客文本流的噪音判别与内容相似性双重检测的过滤方法

微博客作为一种新的用户信息传播载体,在网络舆情发起和传播中起着重要作用。由于用户有意(上传广告)、无意(转发)操作所带来的大量噪音微博和相似微博,对网络舆情分析和用户浏览造成极为不利的影响。检测这些噪音微博和相似微博,对微博数据进行提纯,成为一个亟待解决的问题。基于统计数据分析了噪音微博和相似微博的特点,提出一种面向微博文本流的噪音判别和内容相似性双重检测的过滤方法:通过URL链接、字符率、高频词等特征判别,过滤噪音微博;通过分段过滤和索引过滤的双重内容过滤,检测和剔除相似微博。实验表明该方法能有效地对微博数据进行提纯,高效准确地过滤掉相似微博和噪音微博。     

基于结构信息和时域信息的垃圾网页检测技术

提出一种将结构信息和时域信息综合运用来检测Spam技术的方法,并针对目前流行的Spam技术,从四个月的网络链接图中提取大量的结构和时域信息特征,训练一组检测Spam技术的网页分类器,取得了很好的实验结果。     

基于链接相似度和作弊系数的Spam网页识别算法

Spam网页主要通过链接作弊手段达到提高搜索排名而获利的目的,根据链接作弊的特征,引入链接相似度和作弊系数两个指标来判定网页作弊的可能性。借鉴BadRank算法思想,从Spam网页种子集合通过迭代计算链接相似度和作弊系数,并根据与种子集合的链接指向关系设置权重,将待判定的网页进行度量。最后选取Anti-Trust Rank等算法作对比实验,结果验证了本文算法在准确率和适应性方面优于对比算法。     

Co-Training——内容和链接的Web Spam检测方法

Web spam是指通过内容作弊和网页间链接作弊来欺骗搜索引擎,从而提升自身搜索排名的作弊网页,它干扰了搜索结果的准确性和相关性。提出基于Co-Training模型的Web spam检测方法,使用了网页的两组相互独立的特征——基于内容的统计特征和基于网络图的链接特征,分别建立两个独立的基本分类器;使用Co-Training半监督式学习算法,借助大量未标记数据来改善分类器质量。在WEB SPAM-UK2007数据集上的实验证明:算法改善了SVM分类器的效果。     

基于免疫克隆特征选择和欠采样集成的垃圾网页检测

为解决垃圾网页检测过程中的“维数灾难”和不平衡分类问题,提出一种基于免疫克隆特征选择和欠采样（US）集成的二元分类器算法。首先,使用欠采样技术将训练样本集大类抽样成多个与小类样本数相近的样本集,再将其分别与小类样本合并构成多个平衡的子训练样本集;然后,设计一种免疫克隆算法遴选出多个最优的特征子集;基于最优特征子集对平衡的子样本集进行投影操作,生成平衡数据集的多个视图;最后,用随机森林（RF）分类器对测试样本进行分类,采用简单投票法确定测试样本的最终类别。在WEBSPAM UK-2006数据集上的实验结果表明,该集成分类器算法应用于垃圾网页检测：与随机森林算法及其Bagging和AdaBoost集成分类器算法相比,准确率、F1测度、AUC等指标均提高11%以上;与其他最优的研究结果相比,该集成分类器算法在F1测度上提高2%,在AUC上达到最优。     

基于垃圾邮件发送模型的僵尸网络监测

僵尸网络可以用于发送垃圾邮件,这意味着如果能够对垃圾邮件的发送行为进行建模,也能够很好地检测僵尸网络。本文提出几种垃圾邮件发送模型,对各种垃圾邮件发送行为进行了区分,基于主题特征产生的协同程度提出了僵尸网络指数,其中重点对其在僵尸网络监测效果进行了验证,发现这个模型和指数能够用于有效发现发送邮件的僵尸网络。     

Entity resolution for media metadata based on structural clustering

An increasing amount of media metadata are published by different organizations on the Web which leads to a fragmented dataset landscape. Identifying media metadata from disparate datasets and integrating heterogeneous datasets have many applications but also pose significant challenges. To tackle this problem, entity resolution methods are commonly used as an essential prerequisite for integrating media information from different sources and effectively foster the re-use of existing data sources. While the amount of media metadata published on the Web grows steadily, how to scale it well to large media knowledge bases while maintaining a high matching quality is a critical challenge. This article investigates the relationships between media entities. To that end, the media database is formulated as a knowledge graph with entities as nodes and the associations between related entities as edges. Thus, media entities are grouped into communities by how they share neighbors. Then, a structural clustering-based model is proposed to detect communities and discover anchor vertices as well as isolated vertices. Specifically, an initial seed set of matched anchor vertex pairs is obtained. Furthermore, an iterative propagation approach for identifying the matched entities in the whole graph is developed, where community similarity is introduced into the measure function to control the total measurement of candidate pairs. Therefore, starting with the elements of the initial seed set, the entity resolution algorithm updates the matching information over the whole network along with the neighbor relationships iteratively. Extensive experiments are conducted on real datasets to evaluate how the seed set impacts the matching process and performance. The experiment results show this model can achieve an excellent balance between accuracy and efficiency and is a clear improvement compared to state-of-the-art methods.

     

基于非内容信息的网络关键资源有效定位

网络信息的爆炸式增长，使得当前任何搜索引擎都只可能索引到Web上一小部分数据，而其中又充斥着大量的低质量信息．如何在用户查询无关的条件下找到Web上高质量的关键资源，是Web信息检索面临的挑战．基于大规模网页统计的方法发现，多种网页非内容特征可以用于关键资源页面的定位，利用决策树学习方法对这些特征进行综合，即可以实现用户查询无关的关键资源页面定位．在文本信息检索会议（TREC）标准评测平台上进行的超过19G文本数据规模的实验表明，这种定位方法能够利用20％左右的页面覆盖超过70％的Web关键信息；在仅为全部页面24％的关键资源集合上的检索结果，比在整个页面集合上的检索有超过60％的性能提高．这说明使用较少的索引量获取较高的检索性能是完全可能的．     

基于带权评论图的水军群组检测及特征分析

针对在电子商务平台上检测编写虚假评论的水军群组的问题，提出了基于带权评论图的水军群组检测算法（WGSA）。首先，利用共评论特征构建带权评论图，权重由一系列群组造假指标计算得到；然后，为边权重设置阈值筛选可疑子图；最后，从图的社区结构出发，利用社区发现算法生成最终的水军群组。在Yelp大型数据集上的实验结果表明，与K均值聚类算法（KMeans）、基于密度的噪声应用空间聚类算法（DBscan）以及层次聚类算法相比WGSA算法的准确度更高，同时对检测到水军群组的特征与差异作了分析，发现水军群组的活跃度不同，危害也不同。其中，高活跃度群组危害最大，应重点关注。     

Detecting malicious tweets in trending topics using a statistical analysis of language

Twitter spam detection is a recent area of research in which most previous works had focused on the identification of malicious user accounts and honeypot-based approaches. However, in this paper we present a methodology based on two new aspects: the detection of spam tweets in isolation and without previous information of the user; and the application of a statistical analysis of language to detect spam in trending topics. Trending topics capture the emerging Internet trends and topics of discussion that are in everybody’s lips. This growing microblogging phenomenon therefore allows spammers to disseminate malicious tweets quickly and massively. In this paper we present the first work that tries to detect spam tweets in real time using language as the primary tool. We first collected and labeled a large dataset with 34 K trending topics and 20 million tweets. Then, we have proposed a reduced set of features hardly manipulated by spammers. In addition, we have developed a machine learning system with some orthogonal features that can be combined with other sets of features with the aim of analyzing emergent characteristics of spam in social networks. We have also conducted an extensive evaluation process that has allowed us to show how our system is able to obtain an F-measure at the same level as the best state-of-the-art systems based on the detection of spam accounts. Thus, our system can be applied to Twitter spam detection in trending topics in real time due mainly to the analysis of tweets instead of user accounts.