Stopping the Cyberattack in the Early Stage: Assessing the Security Risks of Social Network Users

Abstract

Online social networks have become an essential part of our daily life. While we are enjoying the benefits from the social networks, we are inevitably exposed to the security threats, especially the serious Advanced Persistent Threat (APT) attack. The attackers can launch targeted cyberattacks on a user by analyzing its personal information and social behaviors. Due to the wide variety of social engineering techniques and undetectable zero-day exploits being used by attackers, the detection techniques of intrusion are increasingly difficult. Motivated by the fact that the attackers usually penetrate the social network to either propagate malwares or collect sensitive information, we propose a method to assess the security risk of the user being attacked so that we can take defensive measures such as security education, training, and awareness before users are attacked. In this paper, we propose a novel user analysis model to find potential victims by analyzing a large number of users’ personal information and social behaviors in social networks. For each user, we extract three kinds of features, i.e., statistical features, social-graph features, and semantic features. These features will become the input of our user analysis model, and the security risk score will be calculated. The users with high security risk score will be alarmed so that the risk of being attacked can be reduced. We have implemented an effective user analysis model and evaluated it on a real-world dataset collected from a social network, namely, Sina Weibo (Weibo). The results show that our model can effectively assess the risk of users’ activities in social networks with a high area under the ROC curve of 0.9607.

A Study of Security Threats in Cloud: Passive Impact of COVID-19 Pandemic

“…Phishing email id is a co mmon practice, where the scammer sends some email pretending an official email, and employee's often get victimized by this type of attack. This attack is caused by any WhatsApp group or messenger also [17]. Phishing can be of several types depending on the nature of attacks.…”

Prediction of The Security Threats in Social Media Using Artificial Intelligence

“…Although this approach is more unpredictable than other machine learning algorithms, it is suitable for this research because it involves complex processing tasks to analyze the social media feeds, posts, and updates of a given user over a while to identify their behavior patterns [16]. Analyzing the type of feeds and commands that a user receives can help determine if they have socialemotional issues like depression and anxiety or their historical engagements with potential cyber criminals [18]. Unsupervised learning techniques are the most suitable for data categorization in this study.…”

“…However, Facebook has its limits based on its user's privacy reasons and international laws that protect users from privacy rights infringement [6]. The online social networking platforms face daily cyber threats from both external parties and the users themselves [18]. Users have been a common target for most online scammers and malicious application developers.…”

“…Apart from data stealing, cybercriminals often take over individual user's accounts and commit activities that are more criminal while the real user is locked out of their accounts. The effects of socially engineered threats are so many, but the conceptual prevention modality can take care of almost every single problem most people experience is online [18].…”

Implementation of Artificial Intelligence to Predict Threats in Social Media Based on User’s Behavior

“…Although this approach is more unpredictable compared to other machine learning algorithms, it is suitable for this research because it involves complex processing tasks to analyze the social media feeds, posts, and updates of a given user over a while to identify their behavior patterns [16]. Analyzing the type of feeds and posts that a user receives can help determine if they have social-emotional issues like depression and anxiety or their historical engagements with potential cybercriminals [18]. Unsupervised learning will be the most effective approach to this study because it identifies the unknown patterns in data and features that can be useful in categorization.…”