{
 "@context": "https://schema.org",
 "@type": "DefinedTerm",
 "@id": "https://wulfkaal.github.io/entities/parameter-leakage",
 "identifier": "kaal:entity:parameter-leakage",
 "name": "Parameter leakage",
 "termCode": "parameter-leakage",
 "inDefinedTermSet": {
  "@id": "https://wulfkaal.github.io/entities/index.json"
 },
 "author": {
  "@type": "Person",
  "name": "Wulf A. Kaal",
  "identifier": "https://orcid.org/0000-0003-0757-275X"
 },
 "dateModified": "2026-07-29",
 "canonicalForm": "https://wulfkaal.github.io/entities/parameter-leakage.md",
 "sha256": "e143c151c3c828756f2a117f58e19b6a47edcf7466fdf91b81f81c0f5d9c8dfe",
 "additionalProperty": [
  {
   "@type": "PropertyValue",
   "name": "status",
   "value": "derived"
  },
  {
   "@type": "PropertyValue",
   "name": "claim_count",
   "value": 2
  },
  {
   "@type": "PropertyValue",
   "name": "work_count",
   "value": 2
  },
  {
   "@type": "PropertyValue",
   "name": "year_span",
   "value": [
    "2024",
    "2024"
   ]
  },
  {
   "@type": "PropertyValue",
   "name": "non_current_claims",
   "value": 0
  }
 ],
 "subjectOf": [
  {
   "@type": "Claim",
   "@id": "https://wulfkaal.github.io/claims/4796714-009",
   "identifier": "kaal:claim:4796714-009",
   "text": "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.",
   "abstract": "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.",
   "citation": "Wulf A. Kaal, AI Governance (2024). SSRN: https://ssrn.com/abstract=4796714",
   "datePublished": "2024",
   "claim_type": "failure",
   "confidence": "evidenced",
   "is_failure_mode": true,
   "scope_conditions": [
    "applies to practical federated learning deployments",
    "risk arises at the parameter exchange step"
   ],
   "source_pdf_sha256": "59fa63bae179e8f9b6b8efbdf90cee28400276512a1b04f9f579a48641305c93",
   "status": "current"
  },
  {
   "@type": "Claim",
   "@id": "https://wulfkaal.github.io/claims/4941807-012",
   "identifier": "kaal:claim:4941807-012",
   "text": "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.",
   "abstract": "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.",
   "citation": "Wulf A. Kaal, AI Governance Via Web3 Reputation System (2024). SSRN: https://ssrn.com/abstract=4941807",
   "datePublished": "2024",
   "claim_type": "failure",
   "confidence": "argued",
   "is_failure_mode": true,
   "scope_conditions": [
    "in federated learning deployments that exchange model parameters",
    "where parameters can be intercepted or mishandled"
   ],
   "source_pdf_sha256": "ab66c1e99a88da1fa36b0c6b536df5184231fe6aa427f3dd53287a4e0ac79853",
   "status": "current"
  }
 ],
 "description": "2 claims in the published works of Wulf A. Kaal carry the concept tag 'parameter-leakage'. Derived node: a roster, not an adjudicated definition."
}