Skip to main content
SpringerLink
Log in

Towards Enabling Trusted Artificial Intelligence via Blockchain

  • Chapter
  • First Online:
Policy-Based Autonomic Data Governance

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 11550))

Abstract

Machine Learning and Artificial Intelligence models are created, trained and used by different entities. The entity that curates data used for the model is frequently different from the entity that trains the model, which is different yet again from the end user of the trained model. The end user needs to trust the received AI model, and this requires having the provenance information about how the model was trained, and the data the model was trained on. This chapter describes how blockchain can be used to track the provenance of training models, leading to better trusted Artificial Intelligence.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 54.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 69.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Mehri, V.A., Tutschku, K.: Flexible privacy and high trust in the next generation internet-the use case of a cloud-based marketplace for AI. In: Swedish National Computer Networking Workshop (2017)

    Google Scholar 

  2. Athalye, A., Sutskever, I.: Synthesizing robust adversarial examples. arXiv preprint arXiv:1707.07397 (2017)

  3. Baracaldo, N., Chen, B., Ludwig, H., Safavi, J.A.: Mitigating poisoning attacks on machine learning models: a data provenance based approach. In: Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, pp. 103–110. ACM (2017)

    Google Scholar 

  4. Barreno, M., Nelson, B., Sears, R., Joseph, A.D., Tygar, J.D.: Can machine learning be secure? In: Proceedings of the 2006 ACM Symposium on Information, Computer and Communications Security, pp. 16–25. ACM (2006)

    Google Scholar 

  5. Biggio, B., Didaci, L., Fumera, G., Roli, F.: Poisoning attacks to compromise face templates. In: 2013 International Conference on Biometrics (ICB), pp. 1–7. IEEE (2013)

    Google Scholar 

  6. Biggio, B., Fumera, G., Roli, F.: Security evaluation of pattern classifiers under attack. IEEE Trans. Knowl. Data Eng. 26(4), 984–996 (2014)

    Article  Google Scholar 

  7. Bray, T., Paoli, J., Sperberg-McQueen, C.M., Maler, E., Yergeau, F.: Extensible markup language (XML). World Wide Web J. 2(4), 27–66 (1997)

    Google Scholar 

  8. Buneman, P., Khanna, S., Wang-Chiew, T.: Why and where: a characterization of data provenance. In: Van den Bussche, J., Vianu, V. (eds.) ICDT 2001. LNCS, vol. 1973, pp. 316–330. Springer, Heidelberg (2001). https://doi.org/10.1007/3-540-44503-X_20

    Chapter  Google Scholar 

  9. Calders, T., Kamiran, F.: Classification with no discrimination by preferential sampling. In: Proceedings of 19th Machine Learning Conference. Belgium and The Netherlands (2010)

    Google Scholar 

  10. Chen, A., Wu, Y., Haeberlen, A., Loo, B.T., Zhou, W.: Architecture, experiences, and the road ahead. In: CIDR, Data Provenance at Internet Scale (2017)

    Google Scholar 

  11. Cretu, G.F., Stavrou, A., Locasto, M.E., Stolfo, S.J., Keromytis, A.D.: Casting out demons: sanitizing training data for anomaly sensors. In: IEEE Symposium on Security and Privacy, SP 2008, pp. 81–95. IEEE (2008)

    Google Scholar 

  12. Fowler, M., Kobryn, C., Scott, K.: UML Distilled: A Brief Guide to the Standard Object Modeling Language. Addison-Wesley Professional, Boston (2004)

    Google Scholar 

  13. Huang, L., Joseph, A.D., Nelson, B., Rubinstein, B.I., Tygar, J.D.: Adversarial machine learning. In Proceedings of the 4th ACM Workshop on Security and Artificial Intelligence, pp. 43–58. ACM (2011)

    Google Scholar 

  14. Jabal, A.A., Bertino, E.: SimP: secure interoperable multi-granular provenance framework. In: 2016 IEEE 12th International Conference on e-Science (e-Science), pp. 270–275. IEEE (2016)

    Google Scholar 

  15. Li, B., Vorobeychik, Y.: Feature cross-substitution in adversarial classification. In: Advances in Neural Information Processing Systems, pp. 2087–2095 (2014)

    Google Scholar 

  16. Liang, X., Shetty, S., Tosh, D., Kamhoua, C., Kwiat, K., Njilla, L.: Provchain: a blockchain-based data provenance architecture in cloud environment with enhanced privacy and availability. In: Proceedings of the 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, pp. 468–477. IEEE Press (2017)

    Google Scholar 

  17. Loo, B.T., et al.: Declarative networking: language, execution and optimization. In: Proceedings of the 2006 ACM SIGMOD International Conference on Management of Data, pp. 97–108. ACM (2006)

    Google Scholar 

  18. Ma, S., et al.: LAMP: data provenance for graph based machine learning algorithms through derivative computation. In Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering, pp. 786–797. ACM (2017)

    Google Scholar 

  19. McDaniel, P.D., Butler, K.R.B., McLaughlin, S.E., Sion, R., Zadok, E., Winslett, M.: Towards a Secure and efficient system for end-to-end provenance. In: TaPP (2010)

    Google Scholar 

  20. McMahan, H.B., Moore, E., Ramage, D., Hampson, S., et al.: Communication-efficient learning of deep networks from decentralized data. arXiv preprint arXiv:1602.05629 (2016)

  21. Pham, T., Solomon, L., Ciricionne, G., Henz, B.: Prevailing in a complex world: ARL’s essential research area on AI & ML. NATO IST-160 (2018)

    Google Scholar 

  22. Ramachandran, A., Kantarcioglu, M.: SmartProvenance: a distributed, blockchain based dataprovenance system. In: Proceedings of the Eighth ACM Conference on Data and Application Security and Privacy, pp. 35–42. ACM (2018)

    Google Scholar 

  23. Satyanarayanan, M.: The emergence of edge computing. Computer 50(1), 30–39 (2017)

    Article  Google Scholar 

  24. Schelter, S., Böse, J.-H., Kirschnick, J., Klein, T., Seufert, S.: Automatically tracking metadata and provenance of machine learning experiments. In: Machine Learning Systems Workshop at NIPS (2017)

    Google Scholar 

  25. Verma, D., Cirincione, G., Pham, T., Ko, B.J.: Generation and management of training data for AI-based algorithms targeted at coalition operations. In Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR IX, vol. 10635, p. 106350U. International Society for Optics and Photonics (2018)

    Google Scholar 

  26. Verma, D., Julier, S., Cirincione, G.: Federated AI for building AI solutions across multiple agencies. arXiv preprint arXiv:1809.10036 (2018)

  27. Verma, D.C., Bent, G.: Policy enabled caching for distributed AI. In: 2017 IEEE International Conference on Big Data (Big Data), pp. 3017–3023. IEEE (2017)

    Google Scholar 

  28. Woodruff, A., Stonebraker, M.: Supporting fine-grained data lineage in a database visualization environment. In: Proceedings of 13th International Conference on Data Engineering, pp. 91–102. IEEE (1997)

    Google Scholar 

  29. Wylot, M., Cudré-Mauroux, P., Hauswirth, M., Groth, P.: Storing, tracking, and querying provenance in linked data. IEEE Trans. Knowl. Data Eng. 29(8), 1751–1764 (2017)

    Article  Google Scholar 

  30. Xiao, H., Xiao, H., Eckert, C.: Adversarial label flips attack on support vector machines. In: ECAI, pp. 870–875 (2012)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. IBM Research, Yorktown Heights, NY, USA

    Kanthi Sarpatwar, Roman Vaculin, Hong Min, Gong Su, Terry Heath, Giridhar Ganapavarapu & Donna Dillenberger

Authors
  1. Kanthi Sarpatwar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Roman Vaculin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hong Min
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Gong Su
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Terry Heath
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Giridhar Ganapavarapu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Donna Dillenberger
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Roman Vaculin .

Editor information

Editors and Affiliations

  1. IBM Research, Yorktown Heights, NY, USA

    Seraphin Calo

  2. Purdue University, West Lafayette, IN, USA

    Elisa Bertino

  3. IBM Research, Yorktown Heights, NY, USA

    Dinesh Verma

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Sarpatwar, K. et al. (2019). Towards Enabling Trusted Artificial Intelligence via Blockchain. In: Calo, S., Bertino, E., Verma, D. (eds) Policy-Based Autonomic Data Governance. Lecture Notes in Computer Science(), vol 11550. Springer, Cham. https://doi.org/10.1007/978-3-030-17277-0_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-17277-0_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-17276-3

  • Online ISBN: 978-3-030-17277-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation