Abstract
Identification of individuals through the use of electronic footprints can be a security vulnerability and also a blessing in disguise. In this work, we have introduced how we can scale up and enhance representations using the generalized form of GAN architecture, capable of learning from generative features and differences in generalized representation. We applied the architecture for accurate person identification and person tracking using a series of browsing footprint patterns and, at the same time, can easily be extended for detection of anomaly, malware, and other browser-based phishing software activity detection. Our proposed GAN network is characterized for the detection of individuals through dissimilarity between real and generated samples and quantification of detected difference, both of which enhanced learning content. Our contributions are in the architectural definition of Generalized Attentive Sequential Generative Adversarial Network (GenAtSeq-GAN), identification of log characteristics for discrimination, and the procedure for scaling up the detection system. We achieved the effectiveness of 80.7% for GenAtSeq, 46 units higher than the older sequential GAN versions.
Similar content being viewed by others
References
Chiranjib S. DeepSeq: learning browsing log data based personalized security vulnerabilities and counter intelligent measures. J Ambient Intell Human Comput. 2019;10(9):3573–602.
Ian G, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair Z, Courville A, Bengio Y. Generative adversarial nets. In: Advances in neural information processing systems. 2014. pp. 2672-80.
Sackmann Stefan, Strüker Jens, Accorsi Rafael. Personalization in privacy-aware highly dynamic systems. Commun ACM. 2006;49(9):32–8.
Rieck Konrad, et al. Automatic analysis of malware behavior using machine learning. J Comput Secur. 2011;19(4):639–68.
Aditya M, Pan C, Hu Z, Schaub F, Ur B, Cranor LF. Assessing privacy awareness from browser plugins. In: Poster at the symposium on usable privacy and security (SOUPS). 2014.
Wang Tao, Goldberg Ian. On realistically attacking Tor with website fingerprinting. Proc Privacy Enhancing Technol. 2016;2016(4):21–36.
Leon Pedro, et al. “Why Johnny can’t opt out: a usability evaluation of tools to limit online behavioral advertising.” Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM;2012
Komiak SYX, Benbasat I. The effects of personalization and familiarity on trust and adoption of recommendation agents. MIS Quarterly. 2006;30(4):941–60.
Kobsa Alfred. Privacy-enhanced web personalization. The adaptive web. Berlin Heidelberg: Springer; 2007. p. 628–70.
Chang CC, et al. Application of neural networks and Kano’s method to content recommendation in web personalization. Expert Syst Appl. 2009;36(3):5310–6.
Patrick DM, Sen S, Spatscheck O, van der Merwe JE, Aiello W, Kalmanek CR. Enterprise security: a community of interest based approach. NDSS. 2006;6:1–3.
Mobasher Bamshad. Data mining for web personalization. Berlin Heidelberg: The adaptive web. Springer; 2007. p. 90–135.
McAteer O This creepy new google feature lets you stalk your entire life’s history. Elite Daily 2016.
Delfina M, Scarano V, Spinelli R How increased awareness can impact attitudes and behaviors toward online privacy protection. In: Social computing (SocialCom), 2013 international conference on. IEEE;2013.
Mcdonald Aleecia M et al. A comparative study of online privacy policies and formats. In: International symposium on privacy enhancing technologies symposium. Springer, Berlin, Heidelberg;2009.
Serge E, Peer E The myth of the average user: Improving privacy and security systems through individualization. In: Proceedings of the 2015 new security paradigms workshop. ACM;2015.
Drew D, Fredrikson M, Livshits Morepriv B Mobile os support for application personalization and privacy. In: Proceedings of the 30th annual computer security applications conference. ACM;2014.
Yingbo S et al. System level user behavior biometrics using Fisher features and Gaussian mixture models. In: Security and Privacy Workshops (SPW), 2013 IEEE. IEEE;2013.
Nguyen Thuy TT, Grenville Armitage. A survey of techniques for internet traffic classification using machine learning. IEEE Commun Surveys Tutorials. 2008;10(4):56–76.
Marforio Claudio, et al. “Personalized security indicators to detect application phishing attacks in mobile platforms; 2015.” arXiv preprint arXiv:1502.06824.
Ke W, Stolfo SJ Anomalous payload-based network intrusion detection. RAID. 4;2004.
Olivarez-Giles N. How to use google’s new my activity privacy tool: Search giant offers users a glimpse of the data it collects from web searches and other services. Wall Street J. 2016.
Stolfo Salvatore J., et al. “Cost-based modeling for fraud and intrusion detection: Results from the JAM project.” DARPA Information Survivability Conference and Exposition, 2000. DISCEX’00. Proceedings. Vol. 2. IEEE;2000.
Maria FA Web Personalization in Intelligent Environments
Mobasher B, et al. Discovery and evaluation of aggregate usage profiles for web personalization. Data Min Knowl Discovery. 2002;6(1):61–82.
Eirinaki Magdalini, Vazirgiannis Michalis. Web mining for web personalization. ACM Transactions on Internet Technology (TOIT). 2003;3(1):1–27.
Florian S et al. Watching them watching me: Browser extensions’ impact on user privacy awareness and concern. In: NDSS Workshop on Usable Security;2016.
Duarte Torres, Sergio Ingmar Weber, Djoerd Hiemstra. Analysis of search and browsing behavior of young users on the web. ACM Trans Web (TWEB). 2014;8(2):7.
António N, et al. Classification of internet users using discriminant analysis and neural networks. In: Next Generation Internet Networks, 2005. IEEE;2005.
Pavel L , Kloft M A framework for quantitative security analysis of machine learning. In: Proceedings of the 2nd ACM workshop on security and artificial intelligence. ACM;2009.
Miriam B et al. Preprocessing and mining web log data for web personalization. In: Congress of the Italian association for artificial intelligence. Springer, Berlin, Heidelberg;2003.
Ajay B, Kay J. Privacy and security in ubiquitous personalized applications. School of Information Technologies, University of Sydney;2004.
Taylor David G, Davis Donna F, Jillapalli Ravi. Privacy concern and online personalization: the moderating effects of information control and compensation. Electron Commerce Res. 2009;9(3):203–23.
Gulyás Gábor György, Gergely Acs, Claude Castelluccia. Near-optimal fingerprinting with constraints. Proc Privacy Enhancing Technol. 2016;2016(4):470–87.
Bruce K, Rogers M, Peppers D. Making it personal: how to profit from personalization without invading privacy. Perseus Publishing;2001.
Mulvenna Maurice D, Anand Sarabjot S, Büchner Alex G. Personalization on the net using web mining: introduction. Commun ACM. 2000;43(8):122–5.
David F, Jain S, Dürmuth M, Biggio B, Giacinto G. Who Are You? A Statistical Approach to Measuring User Authenticity. NDSS. 2016. https://doi.org/10.14722/ndss.2016.23240.
Chiranjib S. ReLGAN: Generalization of Consistency for GAN with Disjoint Constraints and Relative Learning of Generative Processes for Multiple Transformation Learning. arXiv preprint. (2020). arXiv:2006.07809.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The author declares that he has no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sur, C. GenAtSeq GAN with Heuristic Reforms for Knowledge Centric Network with Browsing Characteristics Learning, Individual Tracking and Malware Detection with Website2Vec. SN COMPUT. SCI. 1, 228 (2020). https://doi.org/10.1007/s42979-020-00234-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-020-00234-8