Verifiable Machine Learning Models in Industrial IoT via Blockchain
- The importance of machine learning (ML) has been increasing dramatically for years. From assistance systems to production optimisation to healthcare support, almost every area of daily life and industry is coming into contact with machine learning. Besides all the benefits ML brings, the lack of transparency and difficulty in creating traceability pose major risks. While solutions exist to make the training of machine learning models more transparent, traceability is still a major challenge. Ensuring the identity of a model is another challenge, as unnoticed modification of a model is also a danger when using ML. This paper proposes to create an ML Birth Certificate and ML Family Tree secured by blockchain technology. Important information about training and changes to the model through retraining can be stored in a blockchain and accessed by any user to create more security and traceability about an ML model.
Author: | Jan StodtORCiDGND, Fatemeh StodtORCiDGND, Christoph ReichORCiDGND, Nathan Clarke |
---|---|
DOI: | https://doi.org/10.1007/978-3-031-35644-5_6 |
ISBN: | 978-3-031-35644-5 |
Parent Title (English): | Advanced Computing : 12th International Conference, IACC 2022, Hyderabad, India, December 16–17, 2022, Revised Selected Papers, Part II |
Publisher: | Springer |
Place of publication: | Cham |
Document Type: | Conference Proceeding |
Language: | English |
Year of Completion: | 2022 |
Release Date: | 2023/01/12 |
Tag: | Blockchain; Cybersecurity; Internet of things; Machine learning; Poisoning; Verifiability |
First Page: | 66 |
Last Page: | 84 |
Licence (German): | Urheberrechtlich geschützt |