دنا: استفاده از اهداف شبکه اجتماعی و یادگیری ماشین به منظور تشخیص حساب‌های جعلی و بهبود امنیت شبکه‌های اجتماعی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 استادیار، گروه کامپیوتر، دانشگاه پیام نور تهران، تهران، ایران

2 کارشناسی ارشد، گروه فناوری اطلاعات، دانشگاه پیام نور تهران، تهران، ایران

3 استادیار، گروه کامپیوتر و فناوری اطلاعات، دانشگاه پیام نور تهران، تهران، ایران

چکیده

امروزه همگام با فراگیر شدن شبکه‌های اجتماعی، امنیت این محیط یکی از مسائل مهم و پراهمیت تلقی می‌شود. یکی از چالش‌های امنیتی، ایجاد حساب‌های کاربری جعلی است که موجب آزار و اذیت کاربران شبکه‌های اجتماعی می‌شود. صاحبان این حساب‌های جعلی، اهدافی مانند ایجاد لایک و دنبال‌کننده و یا توزیع اطلاعات غلط با اهداف سیاسی، فرهنگی و اقتصادی را دنبال می‌کنند. در این پژوهش، با هدف بهبود امنیت در شبکه‌های اجتماعی و ارتقای امنیت فضای سایبری، روشی برای بررسی و تشخیص حساب‌های جعلی ارائه خواهد شد. روش پیشنهادی به نام «دنا»، از یک جهت از اهداف شبکه اجتماعی و از طرف دیگر از روش الگوریتم ترکیبی با درخت تصمیم، نزدیک‌ترین همسایه و بیز بهره خواهد گرفت. نتایج از اجرای روش پیشنهادی با الگوریتم ترکیبی، میزان صحت 95/34 درصد را نشان می‌دهد. پایداری و نداشتن overfit از دیگر ویژگی‌های روش پیشنهادی است که در قسمت نتایج اثبات شده است. نتایج این تحقیق می‌تواند در ارائه‌ی راهکارهای پیشگیری از ایجاد حساب‌های جعلی و افزایش امنیت آن به کار رود و منجر به شناخت و بهره‌گیری از تکنیک‌های جدید داده‌کاوی در شبکه‌های اجتماعی گردد و در حوزه‌ی تحلیل داده و داده‌کاوی در شبکه‌های اجتماعی مورد استفاده قرار گیرد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

The enhancement of online social network security by detecting and preventing fake accounts through machine learning

نویسندگان [English]

  • safieh siadat 1
  • vahid rahmaty 2
  • Seyede Fatemeh Noorani 3
1 Assistant Professor, Computer Department, Tehran Payam Noor University, Tehran, Iran
2 Master's degree, Department of Information Technology, Tehran Payam Noor University, Tehran, Iran
3 Assistant Professor, Computer and Information Technology Department, Tehran Payam Noor University, Tehran, Iran
چکیده [English]

Today, with the pervasiveness of social networks, the security of this environment is considered as one of the most important network issues. One of the security challenges is creating fake accounts that harass social media users. The owners of these fake accounts pursue goals such as creating likes and followers or distributing misinformation for political, cultural and economic purposes. In this study, with the aim of improving security in social networks and improving the security of cyberspace, a method for investigating and detecting fake accounts is presented. This method proposes an algorithm that combines the decision tree, the nearest neighbor and Bayes methods. The results of this combined algorithm demonstrate an accuracy of 95.34%. This method has stability and does not suffer from overfit, as proved in the conclusion. The results of this research can be used to provide solutions to prevent the creation of fake accounts and increase account security and lead to the recognition and use of new data mining techniques and also data analysis in social networks. One of the achievements of this research is the method of detecting the falsity of the account and identifying the factors affecting its detection, which has been done using a hybrid algorithm that obtains correct results.

کلیدواژه‌ها [English]

  • Fake accounts
  • data mining
  • detection and prevention of fake accounts
  • cyber security
  • social networks

Smiley face

[1]     Mudasir Ahmad Wani, Muzafar Ahmad Sofi, Suheel Yousuf Wani., “Why Fake Profiles: A Study of Anomalous Users in Different”, categories of Online Social NetworksInternational Journal of Engineering Technology Science and Research, ISSN 2394 – 3386Volume 4, Issue 9 September 2017.
[2]     Staab, S., Domingos, P., Mike, P., Golbeck, J., Ding, L., Finin, T., ... & Vallacher, R. R. “Social Networks Applied”, IEEE Intelligent systems, 20(1), 80-93, 2005.
[3]     Ed Grabianowski, “How Online Dating Works”, http://people.howstuffworks.com/online- dating.htm, last accessed20-07-2016.
[4]     Howard, B., “Analyzing Online Social Networks”, Communications of the ACM,51(11), 2008.
[5]     Kirman, B., Lawson, S., & Linehan, C., “Gaming on and off the Social Graph The Social Structure of Facebook Games”, In Computational Science and Engineering, 2009. CSE'09. International Conference on (Vol. 4, pp.627-632). IEEE, August 2009.
[6]     Aichner, T., & Jacob, F., “Measuring the Degree of Corporate Social Media Use”, International Journal of Market Research,57(2), 257-275, 2015.
[7]     Skeels, M. M., & Grudin, J., “When Social Networks Cross Boundaries: A Case Study of Workplace Use of Facebook and LinkedIn”, In Proceedings of the ACM 2009 international conference on Supporting group work (pp. 95-104). ACM, May 2009.
[8]     Dan Kaplan (January 23, 2012)Twilio Blog , “Match.com Lets Online Daters Call or Text Message without Revealing Their Phone Numbers”, last accessed 15-07-2016.
[9]     “Sky Rock”, http://www.skyrock.com/, last accessed 10-07-2016.
[10] David Matthews, “The world University ranking, Do academic social networks share academics’interests?”, https://www.timeshighereducation.com/features/do-academic-social networks-share- academics-interests, last accessed 21-07-2016.
[11] Mohammad Rezaei, Mohammad Reza. Detection of fake accounts on social networks using principal component analysis and kernel density estimation algorithm (Case study on Twitter social network). Electronic and Cyber Defense, 1399; (): - , (in Persian).
[12] Ghaderi Piraqom, Saeed, Sakhainia, Mehdi, Mansoorizadeh, Muharram. Diagnosis of anomalies in dynamic social networks based on DOR behavioral assessment: 20.1001.1.23224347.1400.9.1.9.6. Electronic and Cyber Defense, 1400; 9 (1): 115-123 , (in Persian).
[13] Ghesmati, Simin. Manage spam on social media using content tagging. Electronic and Cyber Defense, 2014; 2 (2): - , (in Persian).
[14] Snapfish, https://www.snapfish.com/photo-gift/home.
[15] S. Madisetty and M. S. Desarkar, “A Neural Network-Based, Ensemble Approach for Spam Detection in Twitter,” IEEE,Trans. Comput. Soc. Syst., vol. 5, no. 4, pp. 973–984, 2018.
[16] Rohit Kumar Kaliyar, Anurag Goswami, Pratik Narang, Soumendu Sinha, FNDNet – A deep convolutional neural network for fake news detection, Cognitive Systems Research,Volume 61,,2020 Pages 32-44,
[17] Islam, M.R., Liu, S., Wang, X. et al. Deep learning for misinformation detection on online social networks: a survey and new perspectives. Soc. Netw. Anal. Min. 10, 82 (2020). https://doi.org/10.1007/s13278-020-00696-x
[18] Mohammadi, Bahman and Izadkhah, Habib, 1398, Discovery of fake news on social networks using clustering of fake users, Fifth National Conference on Distribution Computing and Big Data Processing, ،https://civilica.com/doc/961918, (in Persian)
[19] Abdullah-All-Tanvir, E. M. Mahir, S. Akhter and M. R. Huq, "Detecting Fake News using Machine Learning and Deep Learning Algorithms," 2019 7th International Conference on Smart Computing & Communications (ICSCC), Sarawak, Malaysia, Malaysia, 2019, pp. 1-5, doi: 10.1109/ICSCC.2019.8843612.

[20] Rohit Kumar Kaliyar, Anurag Goswami, Pratik Narang, Soumendu Sinha, FNDNet – A deep convolutional neural network for fake news detection, Cognitive Systems Research,Volume 61,,2020 Pages 32-44,
[21] Mohammadreza Mohammadrezaei, Mohammad Ebrahim Shiri, Amir Masoud Rahmani, "Identifying Fake Accounts on Social Networks Based on Graph Analysis and Classification Algorithms", Security and Communication Networks, vol. 2018, Article ID 5923156, 8 pages, 2018. https://doi.org/10.1155/2018/5923156.
[22] Vergeer, M., Hermans, L., & Sams, S., “Online Social Networks and Micro-blogging in Political Campaigning:The Exploration of A New Campaign Tool and A New Campaign Style”, Party Politics, 19(3), 477- 501, 2013. 
[23] https://github.com/NikhilCodes/Fake- Twitter-Account-Detection-Keras/tree/master/DATASET.
[24] X. Zhang, S. Zhu, and W. Liang, “Detecting spam and promoting campaigns in the Twitter social network,” Proc. - IEEE Int. Conf. Data Mining, ICDM, pp. 1194–1199, 2012.
[25] Fazil, M., & Abulaish, M. (2018). 
A Hybrid Approach for Detecting Automated Spammers in Twitter. IEEE Transactions on Information Forensics and Security,13 (11), pp. 2719 - 2707. https://doi.org/10.1109/TIFS.2018..2825958.
دوره 10، شماره 1 - شماره پیاپی 37
شماره پیاپی 37، فصلنامه بهار
خرداد 1401
صفحه 85-97
  • تاریخ دریافت: 29 اردیبهشت 1400
  • تاریخ بازنگری: 19 تیر 1400
  • تاریخ پذیرش: 22 آذر 1400
  • تاریخ انتشار: 01 خرداد 1401