Image Analysis for Privacy Assessment in Social Networks

  • Joaquin TavernerEmail author
  • Ramon Ruiz
  • Elena del Val
  • Carlos Diez
  • Jose Alemany
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 802)


Nowadays, the concern about privacy in online social networks has increased. However, the definition of an appropriate privacy policy might be a complex task, especially when several users are involved and have different privacy preferences. This problem usually appears when a user publishes a photo. In this paper, we propose a tool to automatically define the audience of a photo based on a trust metric. This metric uses a set of features (i.e., distance between users, number of people, emotions, etc.) obtained by the image analysis provided by IBM Cloud Visual Recognition Service. In a preliminary experiment considering 40 photos of 4 users, the results show that the proposed trust metric approximates the real trust relationships between users. We plan to integrate the tool into a real online social network.


Image analysis Privacy negotiation Social networks Trust 



This work is partially supported by the Spanish Government project TIN2017-89156-R, by the FPI grants BES-2015-074498 and ACIF/2017/085, and the Post-Doc scholarship with the Ref. SP20170057.


  1. 1.
    Alemany, J., del Val, E., Alberola, J., García-Fornes, A.: Estimation of privacy risk through centrality metrics. Future Gener. Comput. Syst. 82, 63–76 (2017)CrossRefGoogle Scholar
  2. 2.
    Bhattacharjee, B., Boag, S., Doshi, C., Dube, P., Herta, B., Ishakian, V., Jayaram, K., Khalaf, R., Krishna, A., Li, Y.B., et al.: IBM deep learning service. IBM J. Res. Dev. 61(4), 10–11 (2017)Google Scholar
  3. 3.
    Marsh, S.P.: Formalising trust as a computational concept (1994)Google Scholar
  4. 4.
    Mester, Y., Kökciyan, N., Yolum, P.: Negotiating privacy constraints in online social networks. In: Koch, F., Guttmann, C., Busquets, D. (eds.) Advances in Social Computing and Multiagent Systems, pp. 112–129. Springer, Cham (2015)CrossRefGoogle Scholar
  5. 5.
    Nepal, S., Sherchan, W., Paris, C.: STrust: a trust model for social networks. In: 2011 IEEE 10th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), pp. 841–846. IEEE (2011)Google Scholar
  6. 6.
    Sabater, J., Sierra, C.: Reputation and social network analysis in multi-agent systems. In: Proceedings of the First International Joint Conference on Autonomous Agents and Multiagent Systems: Part 1, pp. 475–482. ACM (2002)Google Scholar
  7. 7.
    Shehab, M., Touati, H.: Semi-supervised policy recommendation for online social networks. In: 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 360–367. IEEE (2012)Google Scholar
  8. 8.
    Sherchan, W., Nepal, S., Paris, C.: A survey of trust in social networks. ACM Comput. Surv. (CSUR) 45(4), 47 (2013)CrossRefGoogle Scholar
  9. 9.
    Šitum, M.: Analysis of algorithms for determining trust among friends on social networks. Vienna, June 2014Google Scholar
  10. 10.
    Squicciarini, A.C., Paci, F., Sundareswaran, S.: PriMa: a comprehensive approach to privacy protection in social network sites. Ann. Telecommun. - annales des télécommunications 69(1–2), 21–36 (2014)CrossRefGoogle Scholar
  11. 11.
    Such, J.M., Porter, J., Preibusch, S., Joinson, A.: Photo privacy conflicts in social media: a large-scale empirical study. In: Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, pp. 3821–3832. ACM (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Joaquin Taverner
    • 1
    Email author
  • Ramon Ruiz
    • 1
  • Elena del Val
    • 1
  • Carlos Diez
    • 1
  • Jose Alemany
    • 1
  1. 1.Universitat Politècnica de ValènciaValenciaSpain

Personalised recommendations