kaal:claim:4796714-009

Federated learning does not eliminate privacy risk, because although the data stays decentralized the exchange of model parameters can still expose sensitive information if those parameters are intercepted or improperly handled.

These challenges arise because, while FL keeps data decentralized, it still involves the exchange of model parameters, which could potentially expose sensitive information if intercepted or improperly handled.

Wulf A. Kaal, AI Governance (2024), AI Models: Federated Model, p. 12
https://ssrn.com/abstract=4796714 · source PDF

Wulf A. Kaal, AI Governance (2024). SSRN: https://ssrn.com/abstract=4796714

• applies to practical federated learning deployments
• risk arises at the parameter exchange step

failuresupport: evidencedfailure: parameter exchange leakagefamily: privacy-and-surveillance-riskconsensus-and-security

• restated_by kaal:claim:4941807-012 Federated learning does not eliminate privacy risk, because although the data stays decentralized the protocol...
• extended_by kaal:claim:4855607-006 Federated learning does not eliminate privacy risk: because gradients and partial parameters are transmitted, ...

The quote above is an exact substring of the source PDF, whose sha256 is 59fa63bae179e8f9b6b8efbdf90cee28400276512a1b04f9f579a48641305c93. Extraction method: pdf-text-layer.
Attestation record: colloquium/attestations/86a5ee67b1460935...json
Verify the binding yourself: curl -s https://wulfkaal.github.io/claims/4796714-009.md | sha256sum