A Critical Analysis of Privacy and Security on Social Media

Kumari, Sangeeta; Singh, Sanjiv

doi:10.1109/csnt.2015.21

Cited by 3 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prevalence of the internet has raised concerns about conventional threats. Threats involving malware, spam, phishing, identity theft, and cross-site scripting appear to be a recurring issue [4]. Due to the structure and prevalence of online social networks, these threats have gone viral and could spread quickly among network users.…”

Section: Threatsmentioning

confidence: 99%

Fake Accounts Identification in Mobile Communication Networks Based on Machine Learning

Hassan

Alhalangy²,

Alzahrani³

2023

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

Fake accounts on online social networks are increasing today with an increase in the number of active social network users. Social media websites allow users to share thoughts, facts, views and re-sharing these into various networks. Social media platforms provide users with enormous valuable information but with this great amount of information in social media, many issues like fake profile, online hacking have also grown. The fake profiles in online social sites create fake news and share unwanted material which contains spam links that affect natural users. The massive issue in social media communication networks is spam and it is necessary to identify fake profiles to stop spam. In this paper, a supervised machine learning algorithm called support vector machine (SVM) is used to identify fake accounts on social media effectively. In order to automatically identify fake online profiles, Random Forest classifier is used with SVM. With this concept, it can be applied online easily to identify millions of accounts that cannot be examined manually. The result of this model is compared with other identification techniques and the results show that the proposed algorithm performs better with high precision and recall. This method efficiently safeguards social media networks from online threats and attacks.

show abstract

Section: Threatsmentioning

confidence: 99%