Leveraging social networks to fight spam

Social networks are useful for judging the trustworthiness of outsiders. An automated antispam tool exploits the properties of social networks to distinguish between unsolicited commercial e-mail - spam - and messages associated with people the user knows.     

垃圾邮件的入侵与防范

随着网络技术的迅猛发展,垃圾邮件日益猖獗。为了有效地对垃圾邮件加以打击和防范,该文简单阐述了垃圾邮件的定义和历史,并详细介绍了邮件用户日常应采取的措施。     

A defence scheme against Identity Theft Attack based on multiple social networks

Recently, on-line social networking sites become more and more popular. People like to share their personal information such as their name, birthday and photos on these public sites. However, personal information could be misused by attackers. One kind of attacks called Identity Theft Attack is addressed in on-line social networking sites. After collecting the personal information of a victim, the attacker can create a fake identity to impersonate this victim and cheat the victim’s friends in order to destroy the trust relationships on the on-line social networking sites. In this paper, we propose a scheme to protect users from Identity Theft Attacks. In our work, users’ personal information can be still kept public. It means that this scheme does not violate the nature of the social networks. Compared with previous works, the proposed scheme incurs less overhead for users. Experimental results also demonstrate the practicality of the proposed scheme.     

Clustering based interest prediction in social networks

Efficient interest prediction for social networks is critical for both users and service providers for behavior analysis and a series of extension services. However, most existing approaches are inefficient, incomplete or isolated. In this paper, we propose combination of Gaussian and Markov approaches (namely, GAM) as typical soft computing technology for interest prediction of social intelligent multimedia systems. GAM model considers “the number of posted messages” as the only parameter, and defines selection logic to implement either Gaussian or Markov based approaches. Our proposed solution takes the advantage of Gaussian model in prediction accuracy and computation complexity, and advantage of Markov model in high availability. Further experiments illustrate that our solution achieves higher prediction accuracy of 94.3% (without considering the influence of swing users), with the best result achieved ever.

     

Using honeynodes for defense against jamming attacks in wireless infrastructure-based networks

The advent of wireless networks has brought a new set of security issues with it. One of the most feared of these is the jamming-based attacks. In this paper, we propose a pre-emptive detection strategy using honeynodes and a response mechanism based on the existing Channel Surfing Algorithm [Xu W, Trappe W, Zhang Y, Wood T. Channel surfing and spatial retreats: defenses against wireless denial of service. ACM Wireless Security 2004;80-9] to protect wireless nodes from a jammer. Honeynodes generate dummy communication at a frequency close to the actual frequency of operation, and pre-emptively alert authentic nodes of imminent attacks, so that the authentic nodes can jump to another frequency even before a jammer starts scanning that frequency. The next frequency is selected using a novel approach which uses a hybrid of reactive and proactive channel selection procedures. We have simulated the proposed approach using NS-2. The experimental results further prove a marked improvement in the performance of the proposed system over the Channel Surfing Algorithm in terms of the packet delivery ratio, the jammed duration, control message overhead and the number of channel re-configurations.     

A collaborative defense mechanism against SYN flooding attacks in IP networks

SYN flooding exploits the Transmission Control Protocol (TCP) three-way handshake process by sending many connection requests using spoofed source IP addresses to a victim's host. This keeps that host from handling legitimate requests, causing it to populate its backlog queue with forged TCP connections. In this article, we propose a novel defense mechanism that makes use of the edge routers that are associated with the spoofed IP addresses’ networks to determine whether the incoming SYN–ACK segment is valid. This is accomplished by maintaining a matching table of the outgoing SYNs and incoming SYN–ACKs and also by using the ARP protocol. If an incoming SYN–ACK segment is not valid, the edge router resets the connection at the victim's host, freeing up an entry in the victim's backlog queue, and enabling it to accept other legitimate incoming connection requests. We also present a communication protocol to encourage collaboration between various networks to protect each other. We evaluated the performance of our proposed approach and studied its impact on the network. Our experimental and simulation results showed the efficiency of our proposed collaborative defense mechanism.     

社会网络中基于集合枚举树的k匿名方法

k匿名方法是一种重要的数据隐私保护方法.在应用k匿名方法保护社会网络中用户的隐私时,现有的方法对社会网络的结构进行匿名化处理,当攻击者了解了网络的文本信息后可以很容易识别出用户的身份等隐私信息.为此,提出一种包含结构和文本的k匿名方法.该方法在采用传统的节点度匿名化的基础上,将社会网络中的文本信息分成不同的值域,对每一个值域构建一个全局的层次结构树,对所有的值域采用集合枚举树来优化文本标记泛化时的信息丢失,并针对集合枚举树的特征提出了三种剪枝方法.实验表明,提出的k匿名方法在实现了社会网络的结构和文本匿名化的同时具有较低额的开销.     

基于位置的社会网络中面向时序特征的兴趣点推荐算法

兴趣点推荐是基于位置的社会网络的重要研究内容之一.传统的兴趣点推荐算法或者应用基本的协同过滤方法,或者在基本的协同过滤算法中引入空间特征,而没有充分发掘时序特征对推荐算法的重要性.为了进一步提高兴趣点推荐算法的性能,提出了一种面向时序特征的兴趣点推荐算法.给出了基本的基于用户的协同过滤方法,分别描述了时间特征和空间特征的作用,并给出了相应的模型表示方法;将时间特征和空间特征进行融合,提出了一种联合推荐算法.实验表明,提出的算法与其他相关算法相比,准确率和召回率显著提高,因此更适合兴趣点的推荐服务.     

Supergraph based periodic pattern mining in dynamic social networks

In dynamic networks, periodically occurring interactions express especially significant meaning. However, these patterns also could occur infrequently, which is why it is difficult to detect while working with mass data. To identify such periodic patterns in dynamic networks, we propose single pass supergraph based periodic pattern mining SPPMiner technique that is polynomial unlike most graph mining problems. The proposed technique stores all entities in dynamic networks only once and calculate common sub-patterns once at each timestamps. In this way, it works faster. The performance study shows that SPPMiner method is time and memory efficient compared to others. In fact, the memory efficiency of our approach does not depend on dynamic network’s lifetime. By studying the growth of periodic patterns in social networks, the proposed research has potential implications for behavior prediction of intellectual communities.     

基于机会网络中社交关系的转发机制

由于现有的机会网络转发机制不能完全适应社会网络中基于社交关系的判断与分析,为此通过建立社交关系的分类,构建机会网络中的社会关系树结构模型,提出了一种新的转发机制。该机制设置了节点权重值,由节点所处的层次和社会关系的可利用性及可靠性决定。通过路径权重值,选择最有价值的路径进行消息的传递。通过仿真实验,所提出的转发机制有效地降低了网络中的消息副本数和降低了路由开销。     

Graph coloring and ACO based summarization for social networks

Due to the increasing popularity of contents of social media platforms, the number of posts and messages is steadily increasing. A huge amount of data is generated daily as an outcome of the interactions between fans of the networking platforms. It becomes extremely troublesome to find the most relevant, interactive information for the subscribers. The aim of this work is to enable the users to get a powerful brief of comments without reading the entire list. This paper opens up a new field of short text summarization (STS) predicated on a hybrid ant colony optimization coming with a mechanism of local search, called ACO-LS-STS, to produce an optimal or near-optimal summary. Initially, the graph coloring algorithm, called GC-ISTS, was employed before to shrink the solution area of ants to small sets. Evidently, the main purpose of using the GC algorithm is to make the search process more facilitated, faster and prevents the ants from falling into the local optimum. First, the dissimilar comments are assembled together into the same color, at the same time preserving the information ratio as for an original list of comment. Subsequently, activating the ACO-LS-STS algorithm, which is a novel technique concerning the extraction of the most interactive comments from each color in a parallel form. At the end, the best summary is picked from the best color. This problem is formalized as an optimization problem utilizing GC and ACO-LS to generate the optimal solution. Eventually, the proposed algorithm was evaluated and tested over a collection of Facebook messages with their associated comments. Indeed, it was found that the proposed algorithm has an ability to capture a good solution that is guaranteed to be near optimal and had realized notable performance in comparison with traditional document summarization algorithms.     

Using GMDH-based networks for improved spam detection and email feature analysis

Unsolicited or spam email has recently become a major threat that can negatively impact the usability of electronic mail. Spam substantially wastes time and money for business users and network administrators, consumes network bandwidth and storage space, and slows down email servers. In addition, it provides a medium for distributing harmful code and/or offensive content. In this paper, we explore the application of the GMDH (Group Method of Data Handling) based inductive learning approach in detecting spam messages by automatically identifying content features that effectively distinguish spam from legitimate emails. We study the performance for various network model complexities using spambase, a publicly available benchmark dataset. Results reveal that classification accuracies of 91.7% can be achieved using only 10 out of the available 57 attributes, selected through abductive learning as the most effective feature subset (i.e. 82.5% data reduction). We also show how to improve classification performance using abductive network ensembles (committees) trained on different subsets of the training data. Comparison with other techniques such as neural networks and naïve Bayesian classifiers shows that the GMDH-based learning approach can provide better spam detection accuracy with false-positive rates as low as 4.3% and yet requires shorter training time.     

A check-in shielding scheme against acquaintance inference in location-based social networks

World Wide Web - Location-based social services such as Foursquare and Facebook Place allow users to perform check-ins at places and interact with each other in geography (e.g. check-in together)....     

Collusion-aware detection of review spammers in location based social networks

World Wide Web - To ensure the quality of online review, more and more location-based social networks (LBSNs), like Yelp, have established the filtering systems to detect groups of review spammers....     

基于字典学习的网络社团结构探测算法

复杂网络中的社团结构探测对于理解网络的拓扑结构和功能有重要的意义.本文将字典学习方法应用到社团结构探测问题中,给出一种新的字典学习方法,并将其和其他几种流行的模型与算法作了系统比较.在三种类型的人工数据和来自不同领域的实际数据上的实验结果表明,本文所提出的算法在社团结构探测问题上是非常有效的,具有算法简单、收敛速度快、计算精度高等特点.