Papers by Bandar Alghamdi
Evolving behaviours by spammers on online social networks continue to be a big challenge; this ph... more Evolving behaviours by spammers on online social networks continue to be a big challenge; this phenomenon has consistently received attention from researchers in terms of how they can be combated. On micro-blogging communities, such as Twitter, spammers intentionally change their behavioural patterns and message contents to avoid detection. Understanding the behavior of spammers is important for developing effective approaches to differentiate spammers from legitimate users. Due to the dynamic and inconsistent behaviour of spammers, the problem should be considered from two different levels to properly understand this type of behaviour and differentiate it from that of legitimate users. The first level pertains to the content, and the second, to the users’ demographics. In this paper, we first examine Twitter content relating to a particular topic, extracted from one hashtag, for a dataset comprising both spammers and legitimate users in order to characterise user behaviour with res...
2016 IEEE/WIC/ACM International Conference on Web Intelligence Workshops (WIW), 2016
It is becoming increasingly difficult to ignore the importance of using online social networks (O... more It is becoming increasingly difficult to ignore the importance of using online social networks (OSNs) for various purposes such as marketing, education, entertainment, and business. However, OSNs also open the door for harmful activities and behaviors. Committing financial fraud and propagating malware and spam advertisements are very common criminal actions that people engage in by accessing uniform resource locators (URLs). It has been reported that advanced attackers tend to exploit human flaws rather than system flaws; thus, users are targeted in social media threats by hour. This research aims to understand the state of literature on detecting malicious URLs in OSNs, with a focus on two major aspects: URL and OSN objects. Although the literature presents these two aspects in a different context, this paper will mainly focus on their features in relation to malicious URL detection using classification methods. We firstly review three features of URLs: lexical features, hosts, and domains, then we discuss their limitations. We then introduce social spam analytics and detection models using combined features from both URLs and OSNs, particularly the use of user profiles and posts together with URL features, to enhance the detection of malicious behavior. This combination can help in understanding the interests of the user either explicitly, by stating choices in the profile, or implicitly, by analyzing the post behavior, as the spammers do not maintain a regular interest and tend to exploit events or top trend topics.
Lecture Notes in Computer Science, 2018
Evolving behaviours by spammers on online social networks continue to be a big challenge; this ph... more Evolving behaviours by spammers on online social networks continue to be a big challenge; this phenomenon has consistently received attention from researchers in terms of how it can be combated. On micro-blogging communities, such as Twitter, spammers intentionally change their behavioral patterns and message contents to avoid detection. Many existing approaches have been proposed but are limited due to the characterization of spammers' behaviour with unified features, without considering the fact that spammers behave differently, and this results in distinct patterns and features. In this study, we approach the challenge of spammer detection by utilizing the level of focused interest patterns of users. We propose quantity methods to measure the change in user's interest and determine whether the user has a focused-interest or a diverse-interest. Then we represent users by features based on the level of focused interest. We develop a framework by combining unsupervised and supervised learning to differentiate between spammers and legitimate users. The results of this experiment show that our proposed approach can effectively differentiate between spammers and legitimate users regarding the level of focused interest. To the best of our knowledge, our study is the first to provide a generic and efficient framework to represent user-focused interest level that can handle the problem of the evolving behaviour of spammers.
Uploads
Papers by Bandar Alghamdi