Design Challenges of Trustworthy Artificial Intelligence Learning Systems

  • Matthias R. BrustEmail author
  • Pascal Bouvry
  • Grégoire Danoy
  • El-Ghazil Talbi
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1178)


In the near future, more than two thirds of the world’s population is expected to be living in cities. In this interconnected world, data collection from various sensors is eased up and unavoidable. Handling the right data is an important factor for decision making and improving services. While at the same time keeping the right level of privacy for end users is crucial. This position paper discusses the necessary trade-off between privacy needs and data handling for the improvement of services. Pseudo-anonymization techniques have shown their limits and local computation and aggregation of data seems the way to go. To illustrate the opportunity, the case for a novel generation of clustering algorithms is made that implements a privacy by design approach. Preliminary results of such a clustering algorithm use case show that our approach exhibits a high degree of elasticity.


Artificial Intelligence Trustworthiness Smart cities Data-driven economies 



This work has been partially funded by the joint research programme University of Luxembourg/SnT-ILNAS on Digital Trust for Smart-ICT.


  1. 1.
    ISO/IEC PD TR 24028: Information technology - Artificial Intelligence (AI) - Overview of trustworthiness in Artificial Intelligence. Standard, International Organization for Standardization, Geneva, CHGoogle Scholar
  2. 2.
    Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: OSDI, vol. 16, pp. 265–283 (2016)Google Scholar
  3. 3.
    Andronache, A., Brust, M.R., Rothkugel, S.: Hycast-podcast discovery in mobile networks. In: Proceedings of the 3rd ACM Workshop on Wireless Multimedia Networking and Performance Modeling, pp. 27–34. ACM (2007)Google Scholar
  4. 4.
    Bassett, D.S., Zurn, P., Gold, J.I.: On the nature and use of models in network neuroscience. Nat. Rev. Neurosci. 19, 566–578 (2018) CrossRefGoogle Scholar
  5. 5.
    Blondel, V.D., Guillaume, J.L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks. J. Stat. Mech. Theory Exp. 2008(10), P10008 (2008)CrossRefGoogle Scholar
  6. 6.
    Brust, M.R., Akbaş, M.I., Turgut, D.: VBCA: a virtual forces clustering algorithm for autonomous aerial drone systems. In: 2016 Annual IEEE Systems Conference (SysCon), pp. 1–6. IEEE (2016)Google Scholar
  7. 7.
    Brust, M.R., Frey, H., Rothkugel, S.: Adaptive multi-hop clustering in mobile networks. In: Proceedings of the 4th International Conference on Mobile Technology, Applications, and Systems and the 1st International Symposium on Computer Human Interaction in Mobile Technology, pp. 132–138. ACM (2007)Google Scholar
  8. 8.
    Brust, M.R., Frey, H., Rothkugel, S.: Dynamic multi-hop clustering for mobile hybrid wireless networks. In: Proceedings of the 2nd International Conference on Ubiquitous Information Management and Communication, pp. 130–135. ACM (2008)Google Scholar
  9. 9.
    CEN-CENELEC: Artificial Intelligence, Blockchain and Distributed Ledger Technologies (2019).
  10. 10.
    Chen, J., Brust, M., Kiremire, A., Phoha, V.: Modeling privacy settings of an online social network from a game-theoretical perspective. In: IEEE CollaborateCom (2013)Google Scholar
  11. 11.
    Cihon, P.: Standards for AI governance: international standards to enable global coordination in AI research & development (2019)Google Scholar
  12. 12.
    Dilmaghani, S., Brust, M.R., Danoy, G., Cassagnes, N., Pecero, J., Bouvry, P.: Privacy and security of big data in AI systems: a research and standards perspective. In: Proceedings of the IEEE International Conference on Big Data (IEEE BigData 2019), International Workshop on Privacy and Security of Big Data (PSBD 2019). IEEE BigData (2019)Google Scholar
  13. 13.
    Dilmaghani, S., Brust, M.R., Piyatumrong, A., Danoy, G., Bouvry, P.: Link definition ameliorating community detection in collaboration networks. Front. Big Data 2, 22 (2019)CrossRefGoogle Scholar
  14. 14.
    Celebi, M.E., Aydin, K. (eds.): Unsupervised Learning Algorithms. Springer, Cham (2016). Scholar
  15. 15.
    Hinnefeld, J.H., Cooman, P., Mammo, N., Deese, R.: Evaluating fairness metrics in the presence of dataset bias. arXiv preprint arXiv:1809.09245 (2018)
  16. 16.
    Hong, S., et al.: Discriminating topology in galaxy distributions using network analysis. Mon. Not. R. Astron. Soc. 459(3), 2690–2700 (2016)CrossRefGoogle Scholar
  17. 17.
    Mai, S.T., He, X., Feng, J., Böhm, C.: Efficient anytime density-based clustering. In: Proceedings of the 2013 SIAM International Conference on Data Mining, pp. 112–120 (2013)Google Scholar
  18. 18.
    Pan, L., Zhou, T., Lü, L., Hu, C.K.: Predicting missing links and identifying spurious links via likelihood analysis. Sci. Rep. 6, 22955 (2016)CrossRefGoogle Scholar
  19. 19.
    Rao, B., Minakakis, L.: Evolution of mobile location-based services. Commun. ACM 46(12), 61–65 (2003)CrossRefGoogle Scholar
  20. 20.
    Rubinstein, B.I., et al.: Antidote: understanding and defending against poisoning of anomaly detectors. In: Proceedings of the 9th ACM SIGCOMM Conference on Internet measurement (2009)Google Scholar
  21. 21.
    Sha, Z., et al.: A network-based approach to modeling and predicting product coconsideration relations. Complexity 2018, 14 (2018)CrossRefGoogle Scholar
  22. 22.
    Shirinivas, S., Vetrivel, S., Elango, N.: Applications of graph theory in computer science an overview. Int. J. Eng. Sci. Technol. 2(9), 4610–4621 (2010)Google Scholar
  23. 23.
    Shokri, R., Stronati, M., Song, C., Shmatikov, V.: Membership inference attacks against machine learning models. In: IEEE Symposium on Security and Privacy (SP), pp. 3–18 (2017)Google Scholar
  24. 24.
    Siegler, M.G.: Eric schmidt: Every 2 days we create as much information as we did up to 2003, August 2010. Accessed 7 Mar 2018
  25. 25.
    Steinhardt, J., Koh, P.W.W., Liang, P.S.: Certified defenses for data poisoning attacks. In: Advances in Neural Information Processing Systems (2017)Google Scholar
  26. 26.
    Tramèr, F., Zhang, F., Juels, A., Reiter, M.K., Ristenpart, T.: Stealing machine learning models via prediction APIs. In: 25th USENIX Security Symposium (2016)Google Scholar
  27. 27.
    Wall, M.: Biased and wrong? Facial recognition tech in the dock, July 2019.
  28. 28.
    Wu, F.J., Brust, M.R., Chen, Y.A., Luo, T.: The privacy exposure problem in mobile location-based services. In: Global Communications Conference (GLOBECOM), 2016 IEEE, pp. 1–7. IEEE (2016)Google Scholar
  29. 29.
    Wu, J.: Advances in K-means Clustering: A Data Mining Thinking. Springer, Heidelberg (2012). Scholar
  30. 30.
    Xu, R., Wunsch 2nd, D.: Survey of clustering algorithms. IEEE Trans. Neural Netw. 16(3), 645–678 (2005)CrossRefGoogle Scholar
  31. 31.
    Yang, J., Zhang, X.D.: Predicting missing links in complex networks based on common neighbors and distance. Sci. Rep. 6, 38208 (2016)CrossRefGoogle Scholar
  32. 32.
    Zhang, S.X., Roberts, R.E., Farabee, D.: An analysis of prisoner reentry and parole risk using COMPAS and traditional criminal history measures. Crime Delinq. 60, 167–192 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Matthias R. Brust
    • 1
    Email author
  • Pascal Bouvry
    • 1
    • 2
  • Grégoire Danoy
    • 1
    • 2
  • El-Ghazil Talbi
    • 3
  1. 1.Interdisciplinary Centre for Security Reliability and Trust (SnT)Luxembourg CityLuxembourg
  2. 2.Faculty of Science, Technology and Medicine (FSTM)University of LuxembourgLuxembourg CityLuxembourg
  3. 3.Polytech’Lille, University Lillie - InriaLilleFrance

Personalised recommendations