A comprehensive survey on online social networks security and privacy issues: Threats, machine learning‐based solutions, and open challenges

Abstract

Over the past few years, online social networks (OSNs) have become an inseparable part of people's daily lives. Instead of being passive readers, people are now enjoying their role as content contributors. OSN has permitted its users to share their information including the multimedia content. OSN users can express themselves in virtual communities by providing their opinions and interacting with others. As a consequence, the privacy and security threats in OSNs have emerged as a major concern to the research and business world. In the recent past, a number of survey works have been conducted to discuss different security and privacy threats in OSNs. However, till date, no survey work has been conducted that aims to classify and analyze various machine learning (ML)‐based solutions adapted for the security defense of OSNs. In this survey article, we present a detailed taxonomy with a classification of various works done on various security attacks in OSNs. We then review and summarize the existing state of art survey works on OSN security, and indicate the merits and limitations of these survey works. Next, we review all recent works that aim to provide ML‐based solutions toward defense of security attacks on OSNs. Finally, we discuss the future road‐map on OSN security and provide a comprehensive analysis on the open research issues with feasible measurements and possible solutions.

Where has privacy gone?

“…The latter denotes the fact that our surroundings themselves are no longer what they used to be, and they are not within our personal control, as evident in the growing concerns of privacy and security threats in online social networks. Privacy and security threats in online social networks have emerged as a major concern in the research and business world [10]. People are sharing their personal data on platforms like Facebook and LinkedIn, exposing a vast volume of sensitive information, making these online social network sites a soft target for attackers [10].…”

“…Privacy and security threats in online social networks have emerged as a major concern in the research and business world [10]. People are sharing their personal data on platforms like Facebook and LinkedIn, exposing a vast volume of sensitive information, making these online social network sites a soft target for attackers [10]. Furthermore, privacy inference attacks on online social networks aim at inferring hidden attributes of target users based on released attributes and social relationships [11].…”

An Enhanced Anti-Phishing Technique for Social Media Users: A Multilayer Q-Learning Approach

“…In study [17], the authors presented a structure for discovering dubious conversations on web-based gatherings using a coordinated help vector machine and particle swarm optimization methodology. The study by [18] focuses on detecting harmful URLs inside web-based social networks using client behavior analysis.…”

Exploring the Application Potential of the Large Language Model in Sociological Research: A Case Study of ChatGPT

“…The use of large language models raises privacy challenges in sociological research (Munmun, Sandip, Samiran, Kumar, & Sachin, 2022). With the processing of massive textual data, researchers must pay careful attention to the protection of personal privacy.…”