A Blockchain-Based Trustworthy Model Evaluation Framework for Deep Learning and Its Application in Moving Object Segmentation
Model evaluation is critical in deep learning. However, the traditional model evaluation approach is susceptible to issues of untrustworthiness, including insecure data and model sharing, insecure model training, incorrect model evaluation, centralized model evaluation, and evaluation results that c...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/14/6492 |
| _version_ | 1827731794593579008 |
|---|---|
| author | Rui Jiang Jiatao Li Weifeng Bu Xiang Shen |
| author_facet | Rui Jiang Jiatao Li Weifeng Bu Xiang Shen |
| author_sort | Rui Jiang |
| collection | DOAJ |
| description | Model evaluation is critical in deep learning. However, the traditional model evaluation approach is susceptible to issues of untrustworthiness, including insecure data and model sharing, insecure model training, incorrect model evaluation, centralized model evaluation, and evaluation results that can be tampered easily. To minimize these untrustworthiness issues, this paper proposes a blockchain-based model evaluation framework. The framework consists of an access control layer, a storage layer, a model training layer, and a model evaluation layer. The access control layer facilitates secure resource sharing. To achieve fine-grained and flexible access control, an attribute-based access control model combining the idea of a role-based access control model is adopted. A smart contract is designed to manage the access control policies stored in the blockchain ledger. The storage layer ensures efficient and secure storage of resources. Resource files are stored in the IPFS, with the encrypted results of their index addresses recorded in the blockchain ledger. Another smart contract is designed to achieve decentralized and efficient management of resource records. The model training layer performs training on users’ servers, and, to ensure security, the training data must have records in the blockchain. The model evaluation layer utilizes the recorded data to evaluate the recorded models. A method in the smart contract of the storage layer is designed to enable evaluation, with scores automatically uploaded as a resource attribute. The proposed framework is applied to deep learning-based motion object segmentation, demonstrating its key functionalities. Furthermore, we validated the storage strategy adopted by the framework, and the trustworthiness of the framework is also analyzed. |
| first_indexed | 2024-03-11T00:40:24Z |
| format | Article |
| id | doaj.art-c63e669021dd4f919cf03783ca56c0bf |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T00:40:24Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c63e669021dd4f919cf03783ca56c0bf2023-11-18T21:18:28ZengMDPI AGSensors1424-82202023-07-012314649210.3390/s23146492A Blockchain-Based Trustworthy Model Evaluation Framework for Deep Learning and Its Application in Moving Object SegmentationRui Jiang0Jiatao Li1Weifeng Bu2Xiang Shen3College of Information Engineering, Shanghai Maritime University, Shanghai 201306, ChinaCollege of Information Engineering, Shanghai Maritime University, Shanghai 201306, ChinaCollege of Information Engineering, Shanghai Maritime University, Shanghai 201306, ChinaCollege of Information Engineering, Shanghai Maritime University, Shanghai 201306, ChinaModel evaluation is critical in deep learning. However, the traditional model evaluation approach is susceptible to issues of untrustworthiness, including insecure data and model sharing, insecure model training, incorrect model evaluation, centralized model evaluation, and evaluation results that can be tampered easily. To minimize these untrustworthiness issues, this paper proposes a blockchain-based model evaluation framework. The framework consists of an access control layer, a storage layer, a model training layer, and a model evaluation layer. The access control layer facilitates secure resource sharing. To achieve fine-grained and flexible access control, an attribute-based access control model combining the idea of a role-based access control model is adopted. A smart contract is designed to manage the access control policies stored in the blockchain ledger. The storage layer ensures efficient and secure storage of resources. Resource files are stored in the IPFS, with the encrypted results of their index addresses recorded in the blockchain ledger. Another smart contract is designed to achieve decentralized and efficient management of resource records. The model training layer performs training on users’ servers, and, to ensure security, the training data must have records in the blockchain. The model evaluation layer utilizes the recorded data to evaluate the recorded models. A method in the smart contract of the storage layer is designed to enable evaluation, with scores automatically uploaded as a resource attribute. The proposed framework is applied to deep learning-based motion object segmentation, demonstrating its key functionalities. Furthermore, we validated the storage strategy adopted by the framework, and the trustworthiness of the framework is also analyzed.https://www.mdpi.com/1424-8220/23/14/6492blockchaindeep learningmodel evaluationcomputer visionmoving object segmentation |
| spellingShingle | Rui Jiang Jiatao Li Weifeng Bu Xiang Shen A Blockchain-Based Trustworthy Model Evaluation Framework for Deep Learning and Its Application in Moving Object Segmentation Sensors blockchain deep learning model evaluation computer vision moving object segmentation |
| title | A Blockchain-Based Trustworthy Model Evaluation Framework for Deep Learning and Its Application in Moving Object Segmentation |
| title_full | A Blockchain-Based Trustworthy Model Evaluation Framework for Deep Learning and Its Application in Moving Object Segmentation |
| title_fullStr | A Blockchain-Based Trustworthy Model Evaluation Framework for Deep Learning and Its Application in Moving Object Segmentation |
| title_full_unstemmed | A Blockchain-Based Trustworthy Model Evaluation Framework for Deep Learning and Its Application in Moving Object Segmentation |
| title_short | A Blockchain-Based Trustworthy Model Evaluation Framework for Deep Learning and Its Application in Moving Object Segmentation |
| title_sort | blockchain based trustworthy model evaluation framework for deep learning and its application in moving object segmentation |
| topic | blockchain deep learning model evaluation computer vision moving object segmentation |
| url | https://www.mdpi.com/1424-8220/23/14/6492 |
| work_keys_str_mv | AT ruijiang ablockchainbasedtrustworthymodelevaluationframeworkfordeeplearninganditsapplicationinmovingobjectsegmentation AT jiataoli ablockchainbasedtrustworthymodelevaluationframeworkfordeeplearninganditsapplicationinmovingobjectsegmentation AT weifengbu ablockchainbasedtrustworthymodelevaluationframeworkfordeeplearninganditsapplicationinmovingobjectsegmentation AT xiangshen ablockchainbasedtrustworthymodelevaluationframeworkfordeeplearninganditsapplicationinmovingobjectsegmentation AT ruijiang blockchainbasedtrustworthymodelevaluationframeworkfordeeplearninganditsapplicationinmovingobjectsegmentation AT jiataoli blockchainbasedtrustworthymodelevaluationframeworkfordeeplearninganditsapplicationinmovingobjectsegmentation AT weifengbu blockchainbasedtrustworthymodelevaluationframeworkfordeeplearninganditsapplicationinmovingobjectsegmentation AT xiangshen blockchainbasedtrustworthymodelevaluationframeworkfordeeplearninganditsapplicationinmovingobjectsegmentation |