TY - CHAP
T1 - Ensuring Trustworthy Neural Network Training via Blockchain
AU - Navarro, Edgar
AU - Standing, Kyle J.
AU - Dagher, Gaby G.
AU - Andersen, Tim
N1 - Navarro, Edgar; Standing, Kyle J.; Dagher, Gaby G.; and Andersen, Tim. (2023). "Ensuring Trustworthy Neural Network Training via Blockchain". In 2023 IEEE 5th International Conference on Cognitive Machine Intelligence (CogMI) (31-40). IEEE. https://doi.org/10.1109/CogMI58952.2023.00015
PY - 2023/1/1
Y1 - 2023/1/1
N2 - As Artificial Intelligence prevalence grows, it highlights the risk in relying on compromised models, thereby fueling a growing need to ensure the integrity of trained AI models. In this paper, we present a novel blockchain-based system, designed to authenticate the integrity of trained neural network models. The system addresses the risk of manipulation of a model by strategically re-computing intervals of the training process. Further, the blockchain network provides a traceable, immutable, trusted ledger for cataloging the intricate processes of training and validation. We consider two primary entities involved: ‘submitters’, who submit trained models, and ‘verifiers’, who re-train distinct sections of the submitted models to validate their integrity. The design of the blockchain system emphasizes efficiency by selectively targeting a portion of all training intervals. This is made possible through the use of an innovative weight-analysis algorithm, which applies an Absolute Change approach to identify outliers. We implement our solution to demonstrate that the proposed blockchain system is robust, and the weight-analysis algorithm is accurate and scalable.
AB - As Artificial Intelligence prevalence grows, it highlights the risk in relying on compromised models, thereby fueling a growing need to ensure the integrity of trained AI models. In this paper, we present a novel blockchain-based system, designed to authenticate the integrity of trained neural network models. The system addresses the risk of manipulation of a model by strategically re-computing intervals of the training process. Further, the blockchain network provides a traceable, immutable, trusted ledger for cataloging the intricate processes of training and validation. We consider two primary entities involved: ‘submitters’, who submit trained models, and ‘verifiers’, who re-train distinct sections of the submitted models to validate their integrity. The design of the blockchain system emphasizes efficiency by selectively targeting a portion of all training intervals. This is made possible through the use of an innovative weight-analysis algorithm, which applies an Absolute Change approach to identify outliers. We implement our solution to demonstrate that the proposed blockchain system is robust, and the weight-analysis algorithm is accurate and scalable.
KW - blockchain
KW - machine learning
KW - neural networks
UR - https://scholarworks.boisestate.edu/cs_facpubs/396
UR - https://doi.org/10.1109/CogMI58952.2023.00015
UR - http://www.scopus.com/inward/record.url?scp=85186502151&partnerID=8YFLogxK
U2 - 10.1109/CogMI58952.2023.00015
DO - 10.1109/CogMI58952.2023.00015
M3 - Chapter
T3 - Proceedings - 2023 IEEE 5th International Conference on Cognitive Machine Intelligence, CogMI 2023
SP - 31
EP - 40
BT - 2023 IEEE 5th International Conference on Cognitive Machine Intelligence (CogMI)
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th IEEE International Conference on Cognitive Machine Intelligence, CogMI 2023
Y2 - 1 November 2023 through 3 November 2023
ER -