Loading patent…
AssigneeInternational Business Machines Corporation
InventorsJayaram Kallapalayam Radhakrishnan, Ashish Verma, Zhongshu Gu, Enriquillo Valdez, Pau-Chen Cheng, Hani Talal Jamjoom
Estimating the term…
Techniques for distributed federated learning leverage a multi-layered defense strategy to provide for reduced information leakage. In lieu of aggregating model updates centrally, an aggregation function is decentralized into multiple independent and functionally-equivalent execution entities, each running within its own trusted executed environment (TEE). The TEEs enable confidential and remote-attestable federated aggregation. Preferably, each aggregator entity runs within an encrypted virtual machine that support runtime in-memory encryption. Each party remotely authenticates the TEE before participating in the training. By using multiple decentralized aggregators, parties are enabled to partition their respective model updates at model-parameter granularity, and can map single weights to a specific aggregator entity. Parties also can dynamically shuffle fragmentary model updates at each training iteration to further obfuscate the information dispatched to each aggregator execution entity. This architectural prevents the aggregator from being a single point-of-failure, and serves to protect the model even if all aggregators are compromised.
A method of providing federated learning with reduced information leakage of model aggregation, comprising:
An apparatus, comprising:
A computer program product in a non-transitory computer readable medium for use in a data processing system to provide federated learning with reduced information leakage of model aggregation, the computer program product holding computer program instructions that, when executed by the data processing system, are configured to:
A federated learning system that is secure against information leakage of model aggregation, comprising:
Dependencies are inferred from the claim text.