arXiv · cs.AI · Rodrigo Tertulino, Ricardo Almeida, Laercio Alencar · 8 小时前模型评分38
TBFL：用可验证凭证把关医院身份，抵御联邦学习中的女巫攻击
Trustworthy Blockchain-based Federated Learning for Electronic Health Records: Identity-Gated Participation against Sybil Attacks
导读
研究团队提出 TBFL 框架，由权威机构向医院去中心化标识符签发可验证凭证（VC，Verifiable Credential），并通过智能合约注册表只接纳持证方提交的模型更新。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
应用领域：医疗与生命科学
事件类型：研究发布
证据摘录
- “We present TBFL, a framework in which an accountable authority issues Verifiable Credentials to the Decentralized Identifiers of hospitals, and a smart-contract registry on a peer-to-peer ledger admits model updates only from credentialed senders.”
- “On a local node, on-chain checks added about 1% to training time; fees made training impractical on a public mainnet but affordable on a rollup.”
- “It did not stop credentialed hospitals that flipped their own labels, whereas the gate followed by the coordinate-wise median withstood both.”
来源：arXiv · cs.AI · arxiv.org