{"id":21730898,"url":"https://github.com/ranxi2001/cremodeva","last_synced_at":"2026-05-21T14:14:07.392Z","repository":{"id":209834500,"uuid":"725028727","full_name":"ranxi2001/Cremodeva","owner":"ranxi2001","description":"BC4AI：Blockchain Used to Guarantee Credibility of AI Model Evaluations;利用区块链来保证算法模型的真实性","archived":false,"fork":false,"pushed_at":"2023-12-03T12:16:37.000Z","size":90,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-20T23:28:45.408Z","etag":null,"topics":["ai","blockchain","credibility","deep-learning","machine-learning","modelevaluation"],"latest_commit_sha":null,"homepage":"","language":"Solidity","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ranxi2001.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-11-29T09:40:41.000Z","updated_at":"2023-11-30T09:22:42.000Z","dependencies_parsed_at":"2023-11-29T12:25:01.907Z","dependency_job_id":"c7a37228-45cb-4611-a75c-a2ceb5e4e2ca","html_url":"https://github.com/ranxi2001/Cremodeva","commit_stats":null,"previous_names":["ranxi2001/cremodeva"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ranxi2001/Cremodeva","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ranxi2001%2FCremodeva","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ranxi2001%2FCremodeva/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ranxi2001%2FCremodeva/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ranxi2001%2FCremodeva/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ranxi2001","download_url":"https://codeload.github.com/ranxi2001/Cremodeva/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ranxi2001%2FCremodeva/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33303284,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-21T12:23:38.849Z","status":"ssl_error","status_checked_at":"2026-05-21T12:22:11.673Z","response_time":62,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","blockchain","credibility","deep-learning","machine-learning","modelevaluation"],"created_at":"2024-11-26T04:18:43.313Z","updated_at":"2026-05-21T14:14:07.368Z","avatar_url":"https://github.com/ranxi2001.png","language":"Solidity","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Cremodeva\nBC4AI：Blockchain Used to Guarantee Credibility of AI Model Evaluations\n\n这是我的毕业论文项目，十分欢迎对这个项目感兴趣的大佬加入开发。\n\n这个项目的目的是实现算法模型的可信度保障，包括测试结果的真实性，保障论文模型的效果是真实可信的。\n\n## 项目目标\n\n### 项目思路\n\n1. **集成区块链和深度学习**：利用区块链技术提升深度学习模型的可信度和透明度，同时保护模型和数据的隐私。\n2. **去中心化数据存储**：使用如IPFS这样的去中心化存储解决方案来存储数据，确保数据的持久性和可访问性。\n3. **模型和代码的安全存储与共享**：确保训练完成的模型和评估代码的安全性和完整性。\n4. **可审计的模型评估过程**：构建一个透明且可审计的模型评估流程，以提高模型评估的公信力。\n5. **社区参与的模型评价机制**：引入社区投票机制，类似于学术论文的同行评审，以提高模型的可信度。\n\n### 需要实现的功能\n\n1. **数据托管（IPFS）**：\n   - 使用IPFS等去中心化存储技术托管数据。\n   - 确保数据的持久性和难以篡改。\n2. **模型评估真实性保证**：\n   - 通过智能合约或其他区块链机制来确保评估过程的真实性和透明度。\n3. **代码封存**：\n   - 安全存储训练完成的模型和评估部分的代码。\n   - 通过区块链技术确保代码的不可篡改和易于验证。\n4. **模型真实性投票（适用于论文发布审稿）**：\n   - 实施基于社区的模型评价机制，类似于学术论文的同行评审。\n   - 通过投票机制来提升模型的可信度。\n5. **模型和代码一致性检验**：\n   - 验证存储的模型和代码是否一致，确保其未被非法修改。\n   - 使用哈希等技术确保一致性。\n6. **多次测试取平均值数据认证**：\n   - 进行多次模型测试以获取更准确和可靠的评估结果。\n   - 通过平均值或其他统计方法提高数据的可信度。\n\n### 参考文献\n\n\u003e [1] 冯晨. 基于区块链的可信深度学习隐私保护方案研究[D]. 福建师范大学, 2021.\n\u003e\n\u003e [2] 卢浩文. 基于图像匹配和区块链存储的大仪实验可信度研究[D]. 杭州电子科技大学, 2023.\n\u003e\n\u003e [3] Jiang R, Li J, Bu W, et al. A Blockchain-Based Trustworthy Model Evaluation Framework for Deep Learning and Its Application in Moving Object Segmentation[J]. Sensors, 2023, 23(14): 6492.\n\u003e\n\u003e [4] Wang T, Du M, Wu X, 等. An Analytical Framework for Trusted Machine Learning and Computer Vision Running With Blockchain[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2020: 6-7.\n\u003e\n\u003e [5] Shafay M, Ahmad R W, Salah K, et al. Blockchain for deep learning: review and open challenges[J]. Cluster Computing, 2023, 26(1): 197-221.\n\u003e\n\u003e [6] Weng J, Weng J, Zhang J, 等. DeepChain: Auditable and Privacy-Preserving Deep Learning with Blockchain-Based Incentive[J]. IEEE Transactions on Dependable and Secure Computing, 2021, 18(5): 2438-2455.\n\u003e\n\u003e [7] Goel A, Agarwal A, Vatsa M, 等. DeepRing: Protecting Deep Neural Network With Blockchain[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2019: 0-0.\n\n## 项目计划\n\n### 初期工作[12月底]\n\n#### 1.技术选型+技术学习\n\n**开发工具**：`Vscode`+`HardHat`+`Node.js`\n\n**编程语言**：`Solidity`+`Python`+`JavaScript`\n\n\n\n### 中期工作[2月底]\n\n\n\n### 后期工作[4月底]\n\n1. 毕业论文撰写\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Franxi2001%2Fcremodeva","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Franxi2001%2Fcremodeva","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Franxi2001%2Fcremodeva/lists"}