Identifying Fake Profile in Online Social Network: An Overview and Survey

Joshi, Shruti; Nagariya, Himanshi Gupta; Dhanotiya, Neha; Jain, Sarika

doi:10.1007/978-981-15-6315-7_2

Cited by 13 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A detection method has been proposed which can effectively detect cloned and fake profiles in Online Social Networks [22]. Online Social Networks (OSNs) are used by a wide range of people, from children to adults, and can be misused in various ways.Researchers have developed systems to detect fake accounts on OSNs, relying on account features and classification algorithms.This paper provides an overview of various studies done in this direction and a survey of all the techniques already used and can be used in the future [23]. Proposed a detection technique called Fake Profile Recognizer (FPR) for verifying the identity of profiles and detecting fake profiles in OSNs.Detection method based on utilizing Regular Expression (RE) and Deterministic Finite Automaton (DFA) approaches.Evaluated proposed detection technique on three datasets types of OSNs with high Precision, Recall, accuracy, and low False Positive Rates (FPR) [24].…”

Section: Related Workmentioning

confidence: 99%

TSMFPMSM: Design of a Temporal Sentiment analysis Model for identification of Fake Profiles from Multimodal Social Media interfaces

BHRUGUMALLA¹,

Mohanty²

2023

Preprint

View full text Add to dashboard Cite

The growing number of fake profiles on social media has made it necessary to develop intelligent models for identifying and removing them. This study proposes a novel approach for identifying fake profiles using temporal sentiment analysis. The model collects large datasets from various social media platforms, which are then processed using an ensemble sentiment analysis engine. This produces temporal sentiment patterns, which are used to train a 1D Convolutional Neural Network (1D CNN) for the efficient identification of fake profiles. The model is based on the theory that the data communicated by fake users always converges, and was observed to improve fake-profile detection accuracy by 5.9% with higher precision and recall compared to standard methods. This proposed model can be applied to multimodal social media interfaces.

show abstract

Section: Related Workmentioning

confidence: 99%

TSMFPMSM: Design of a Temporal Sentiment analysis Model for identification of Fake Profiles from Multimodal Social Media interfaces

BHRUGUMALLA¹,

Mohanty²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Towards improving the performance in detecting fake profiles different normalization approaches like Min-Max and Z score has been presented. The method is evaluated with the twitter data set [1,2]. A machine learning model is presented towards securing the social media accounts which calculate followers and friends of any account to measure the trust of any user [3].…”

Section: Related Workmentioning

confidence: 99%

Real Time Profile Analysis and Fake Detection Model for Improved Profile Security in Online Social Networks

2022

IJIES

View full text Add to dashboard Cite

The problem of social network security has been well studied. Numbers of approaches are identified towards securing the profile of social network users and identifying the fake profiles. Still the methods suffer to produce efficient results on detecting fake profiles. To improve the performance, an efficient profile analysis and fake detection model is presented in this article. The proposed Real Time Profile Analysis and Fake Detection Model (RTPAFDM) works on three phases: first the Post Level Trust Analysis (PLTA) is performed, which monitors the post updated on every day and share the posts internally with other users to claim the trustworthy of the post which computes the value of User Post Trust Weight (UPTW); second the method performs Profile Level Trust Analysis (PrLTA) which extracts the profile information like user name, personal details, contact details and friends list. According to the information extracted, the method searches on the entire social network to measure the Profile Match Similarity (PSM). Based on the PSM value, the method would identify the originality of the profile; finally, the method performs Profile Historic Trust Analysis (PHTA) which works on the earlier posts made and their truth values. It computes the value of Historical Trusted Post Weight (HTPW). Using the result of all these trust analysis values, the profile security and fake detection is performed. The method is evaluated with Twitter data set and achieved fake detection accuracy up to 97% and supports the improvement profile security efficiently.

show abstract

“…In situations involving Advanced Persistent Threats, fake identities on social media are frequently used to transmit malwares or suspicious links. Furthermore, they are employed in various nefarious activities like sending spams and spam emails, and in certain applications, to promote and inflate the number of users (Joshi et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Machine learning for detecting fake accounts and genetic algorithm-based feature selection

Sallah,

Abdellaoui Alaoui,

C.K. Tekouabou

et al. 2024

Data & Policy

View full text Add to dashboard Cite

People rely extensively on online social networks (OSNs) in Africa, which aroused cyber attackers’ attention for various nefarious actions. This global trend has not spared African online communities, where the proliferation of OSNs has provided new opportunities and challenges. In Africa, as in many other regions, a burgeoning black-market industry has emerged, specializing in the creation and sale of fake accounts to serve various purposes, both malicious and deceptive. This paper aims to build a set of machine-learning models through feature selection algorithms to predict the fake account, increase performance, and reduce costs. The suggested approach is based on input data made up of features that describe the profiles being investigated. Our findings offer a thorough comparison of various algorithms. Furthermore, compared to machine learning without feature selection and Boruta, machine learning employing the suggested genetic algorithm-based feature selection offers a clear runtime advantage. The final prediction model achieves AUC values between 90% and 99.6%. The findings showed that the model based on the features chosen by the GA algorithm provides a reasonable prediction quality with a small number of input variables, less than 31% of the entire feature space, and therefore permits the accurate separation of fake from real users. Our results demonstrate exceptional predictive accuracy with a significant reduction in input variables using the genetic algorithm, reaffirming the effectiveness of our approach.

show abstract

Identifying Fake Profile in Online Social Network: An Overview and Survey

Cited by 13 publications

References 17 publications

TSMFPMSM: Design of a Temporal Sentiment analysis Model for identification of Fake Profiles from Multimodal Social Media interfaces

TSMFPMSM: Design of a Temporal Sentiment analysis Model for identification of Fake Profiles from Multimodal Social Media interfaces

Real Time Profile Analysis and Fake Detection Model for Improved Profile Security in Online Social Networks

Machine learning for detecting fake accounts and genetic algorithm-based feature selection

Contact Info

Product

Resources

About