Filters








117 Hits in 5.7 sec

Preserving Privacy in Multimedia Social Networks Using Machine Learning Anomaly Detection

Randa Aljably, Yuan Tian, Mznah Al-Rodhaan
2020 Security and Communication Networks  
The models could use further information derived from the user's profiles to detect anomalous users.  ...  In this paper, we implement a privacy preservation algorithm that incorporates supervised and unsupervised machine learning anomaly detection techniques with access control models.  ...  In addition, the anomalies are not labeled and they are distributed all over the dataset. Furthermore, it is normal for a user's behavior to evolve and change over time.  ... 
doi:10.1155/2020/5874935 fatcat:zjuxk6t7pnbtpgcorsoaigiwam

Role-Aware Information Spread in Online Social Networks

Alon Bartal, Kathleen M. Jagodnik
2021 Entropy  
OSNs; and (iv) describe how information spread models enable useful applications in OSNs such as detecting influential users.  ...  Users assume various roles based on their behaviors while engaging with information in these OSNs.  ...  Users' interactions change and evolve over time [31, 89] , and can be characterized as roles that describe user behavior [31, 90] .  ... 
doi:10.3390/e23111542 pmid:34828240 pmcid:PMC8618065 fatcat:sxllkrngpvcgzfn3whjekzo75a

A Comprehensive Survey of Time Series Anomaly Detection in Online Social Network Data

Md Rafiqul, Naznin Sultana, Mohammad Ali, Prohollad Chandra, Bushra Rahman
2017 International Journal of Computer Applications  
In the field of data mining, the social network is one of the complex systems that poses significant challenges in this area. Time series anomaly detection is one of the critical applications.  ...  We provide some applications, challenging issues and existing methods for time series anomaly detection.  ...  An event within a time series may be anomalous; a subsequence within a time series may be anomalous; or an entire time series may be anomalous with respect to a set of normal time series.b.  ... 
doi:10.5120/ijca2017915989 fatcat:2h2darlw3jd7jedvb723p42vtm

Sneak into Devil's Colony- A study of Fake Profiles in Online Social Networks and the Cyber Law [article]

Mudasir Ahmad Wani, Suraiya Jabin, Ghulam Yazdani, Nehaluddin Ahmadd
2018 arXiv   pre-print
Daily reports of the security and privacy threats in the OSNs demand not only the intelligent automated detection systems that can identify and alleviate fake profiles in real time but also the reinforcement  ...  In order to design fake profile detection systems, we have highlighted different category of fake profile features which are capable to distinguish different kinds of fake entities from real ones.  ...  profile detection in OSNs.  ... 
arXiv:1803.08810v1 fatcat:c6kqphdeyvfkfhho4lkoxl7zay

Review and Analysis on Filtering of Unwanted Multimedia Messages from Online Social Network User Walls

Martand Ratnam
2021 International Journal for Research in Applied Science and Engineering Technology  
An information filtering system proposed in this paper may allow OSN users to control the posting and commenting on their walls directly.  ...  Abstract: When it comes to sharing and exchanging various types of information, online social networks (OSNs) have become an increasingly popular and interactive medium in today's world.  ...  Spam detection in OSNs is done using the usual methods. Manajit et al. conducted a study on the current state of spam detection in social networks (2016).  ... 
doi:10.22214/ijraset.2021.39629 fatcat:kn2e4ak2nnhepcatxpvtfy6spm

CredSaT: Credibility Ranking of Users in Big Social Data incorporating Semantic Analysis and Temporal Factor [article]

Bilal Abu-Salih, P. Wongthongtham, KY Chan, Z. Dengya
2018 arXiv   pre-print
Further, CredSaT shows the capacity in capturing spammers and other anomalous users.  ...  The widespread use of big social data has pointed the research community in several significant directions.  ...  This is logical since the user's interest(s) could change, and their knowledge evolves over time.  ... 
arXiv:1808.01413v1 fatcat:3x2anxc6yfeg3gg2of5skmjlum

A sneak into the Devil's Colony - Fake Profiles in Online Social Networks [article]

Mudasir Ahmad Wani, Suraiya Jabin
2017 arXiv   pre-print
At the same time, various kinds of spammers are also equally attracted towards these OSNs.  ...  From the OSN service provider point of view, fake profiles affect the overall reputation of the network in addition to the loss of bandwidth.  ...  of OSN graph over time.  ... 
arXiv:1705.09929v2 fatcat:sjz4ux7mffd43pzgzdoe3gx3oy

Diagnosing Venomous Facebook Applications

K. Saiprasad
2016 International Journal Of Engineering And Computer Science  
Our main contribution is in evolving FRAppE-Facebook's Rigorous Application Evaluator-feasibly the first tool focused on detecting malicious apps on facebook.  ...  The issue is already valid, as we find that at least 13% of apps in our dataset are malicious. So far, the research center has concentrated on detecting malicious posts and campaigns.  ...  Others have proposed a honey-pot-based approach to detect spam accounts on OSNs. Yardi et al. analyzed behavioral patterns among spam accounts in Twitter.  ... 
doi:10.18535/ijecs/v5i11.67 fatcat:4zqx2d66n5aejampdytg4taz4i

A survey of data mining and social network analysis based anomaly detection techniques

Ravneet Kaur, Sarbjeet Singh
2016 Egyptian Informatics Journal  
Anomalous activities in social networks represent unusual and illegal activities exhibiting different behaviors than others present in the same structure.  ...  Online Social Networks (OSNs) have fetched the interest of researchers for their analysis of usage as well as detection of abnormal activities.  ...  Sometimes, the normal behavior does not result in any network change; then, any neighborhood changes may also predict an anomalous behavior.  ... 
doi:10.1016/j.eij.2015.11.004 fatcat:jixqyc6p5vfx5kkiczcwtt32fy

Realistic Aspects of Simulation Models for Fake News Epidemics over Social Networks

Quintino Francesco Lotito, Davide Zanella, Paolo Casari
2021 Future Internet  
Moreover, we emphasize that bots dramatically speed up the spreading process and that time-varying engagement and network access change the effectiveness of fake news spreading.  ...  Specifically, we introduce agents with the role of influencers and bots in the model and consider the effects of dynamical network access patterns, time-varying engagement, and different degrees of trust  ...  Data Availability Statement: All results in this paper can be derived from our simulation software, publicly available on GitHub (https://github.com/FraLotito/fakenews_simulator, accessed on 16 March 2021  ... 
doi:10.3390/fi13030076 fatcat:rpbvqozje5fxhnhm5h2ylbqcaa

A Survey of Social Network Forensics

Umit Karabiyik, Muhammed Canbaz, Ahmet Aksoy, Tayfun Tuna, Esra Akbas, Bilal Gonen, Ramazan Aygun
2016 Journal of Digital Forensics, Security and Law  
This will help digital forensics investigators to predict, detect and even prevent any criminal activities in different forms.  ...  It also provides awareness and defense methods for OSN users in order to protect them against to social attacks.  ...  Since OSNs also allow posting images, videos, and audio, OSN service providers should detect harmful messages and postings and remove or block them in real time.  ... 
doi:10.15394/jdfsl.2016.1430 fatcat:wrlinyds4nf6zl7nybbyujqn64

Harvesting the Low-hanging Fruits: Defending Against Automated Large-Scale Cyber-Intrusions by Focusing on the Vulnerable Populations

Hassan Halawa, Konstantin Beznosov, Yazan Boshmaf, Baris Coskun, Matei Ripeanu, Elizeu Santos-Neto
2016 Zenodo  
To change the status quo, we propose to identify, even if imperfectly, the vulnerable user population, that is, the users that are likely to fall victim to such attacks.  ...  Once identified, information about the vulnerable population can be used in two ways.  ...  ISPs can place such "honeypots" under much closer scrutiny than typical users in order to detect evolving threats.  ... 
doi:10.5281/zenodo.3264717 fatcat:pqzoajvmefblbdz6yqrfrdnl7m

An Effective Technique to Identify Anomalous Accounts on Social Networks using Bloom Filter

Sarbjeet Kaur, Prabhjot Kaur
2017 International Journal of Computer Applications  
The simulation is being performed in MATLAB and it is being analyzed that accuracy is increased and execution time is reduced.  ...  The anomaly detection is the technique which is applied to detect malicious activities from the social network data.  ...  A dynamic anomaly exists with respect to past network behavior in which changes happen in the network with the passage of time.  ... 
doi:10.5120/ijca2017913732 fatcat:pb2q7zsnyvfgdlap2rar4bmemm

The Paradigm-Shift of Social Spambots

Stefano Cresci, Roberto Di Pietro, Marinella Petrocchi, Angelo Spognardi, Maurizio Tesconi
2017 Proceedings of the 26th International Conference on World Wide Web Companion - WWW '17 Companion  
Here, for the first time, we extensively study this novel phenomenon on Twitter and we provide quantitative evidence that a paradigm-shift exists in spambot design.  ...  First, we measure current Twitter's capabilities of detecting the new social spambots.  ...  As evolving spammers became clever in escaping detection, for instance by changing discussion topics and posting activities, researchers kept the pace and proposed complex models, such as those based on  ... 
doi:10.1145/3041021.3055135 dblp:conf/www/CresciPPST17 fatcat:cdealjf6rvds7ireyt2u56fr2i

Network Attack Analysis and the Behaviour Engine

A. Benham, H. Read, I. Sutherland
2013 2013 IEEE 27th International Conference on Advanced Information Networking and Applications (AINA)  
The final goal of the research will be to develop a behaviour engine/intrusion detection solution for pre-emptive counter-measures to anomalous behaviour from within or without a network.speed.  ...  capture data, to detect data exfiltration attempts over covert channelling.  ...  SUMMARY This paper has demonstrated that the current state of the art in anomaly network intrusion detection and prevention technology possess deficiencies in satisfactorily detecting anomalous intrusions  ... 
doi:10.1109/aina.2013.157 dblp:conf/aina/BenhamRS13 fatcat:zwih4tl2k5chzgvy7qczzf4fzq
« Previous Showing results 1 — 15 out of 117 results