# More or Less? Predict the Social Influence of Malicious URLs on Social Media

## TL;DR

This paper investigates how social recommendation systems influence the spread of malicious URLs on Facebook, using temporal features to predict user behavior with over 75% accuracy, and classifies URLs by damage level.

## Contribution

It introduces a prediction framework based on temporal features to assess the likelihood of malicious URL spread, and categorizes URLs by potential damage in OSNs.

## Key findings

- Prediction accuracy exceeds 75% for user behavior
- Malicious URLs can be classified by damage level
- Social recommendation systems influence URL dissemination

## Abstract

Users of Online Social Networks (OSNs) interact with each other more than ever. In the context of a public discussion group, people receive, read, and write comments in response to articles and postings. In the absence of access control mechanisms, OSNs are a great environment for attackers to influence others, from spreading phishing URLs, to posting fake news. Moreover, OSN user behavior can be predicted by social science concepts which include conformity and the bandwagon effect. In this paper, we show how social recommendation systems affect the occurrence of malicious URLs on Facebook. We exploit temporal features to build a prediction framework, having greater than 75% accuracy, to predict whether the following group users' behavior will increase or not. Included in this work, we demarcate classes of URLs, including those malicious URLs classified as creating critical damage, as well as those of a lesser nature which only inflict light damage such as aggressive commercial advertisements and spam content. It is our hope that the data and analyses in this paper provide a better understanding of OSN user reactions to different categories of malicious URLs, thereby providing a way to mitigate the influence of these malicious URL attacks.