# kaal:claim:4941807-012

**Claim.** Federated learning does not eliminate privacy risk, because although the data stays decentralized the protocol still exchanges model parameters, and those parameters can expose sensitive information if intercepted or improperly handled.

**Type.** failure  **Support.** argued

**Holds when.**

- in federated learning deployments that exchange model parameters
- where parameters can be intercepted or mishandled

**Source quote.**

> 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.

**From.** Wulf A. Kaal, *AI Governance Via Web3 Reputation System* (2024), Federated Model, page 12

**Cite as.** Wulf A. Kaal, AI Governance Via Web3 Reputation System (2024). SSRN: https://ssrn.com/abstract=4941807

**Verify.** sha256 of source PDF `ab66c1e99a88da1fa36b0c6b536df5184231fe6aa427f3dd53287a4e0ac79853` at https://raw.githubusercontent.com/wulfkaal/Academic-Papers/main/papers/pdf/Kaal%20-%202024%20-%20AI%20Governance%20Via%20Web3%20Reputation%20System.pdf

**Failure mode.** parameter exchange leakage  (family: privacy-and-surveillance-risk)

**Topics.** consensus-and-security, decentralization, ai-and-agents

**Keywords.** federated-learning, privacy, parameter-leakage, security, decentralized-ai

**Related claims.**

- restates: https://wulfkaal.github.io/claims/4796714-009
- contested_by: https://wulfkaal.github.io/claims/5095633-017
- restates: https://wulfkaal.github.io/claims/4855607-006

**Canonical form.** This markdown file is the canonical hashed representation of the claim. Its sha256 is the content hash used for attestation.