AI Papers Atlas Wave 1
W7155512583 Working papers AI × management and organizations

TaxFL: Federated Learning and Federated Graph Intelligence for Cross-Border Tax and AML Compliance — A privacy-preserving reference architecture and utility-frontier analysis for collaborative tax and AML risk analytics

Pedro Augusto Frantz

Also recorded as: doi:10.2139/ssrn.6624799 · ssrn:6624799

ssrn abstract page · 2026-04-24

Source of record — papers.ssrn.com See it on the corpus view
Recorded claims
3
coded from the inspected source
Evidence classes
2
ssrn-abstract-page, ssrn-ejournal-listing
Recorded limitations
4
stated, never hidden

From the hash-bound evidence releases

Recorded claims

Each claim states what the inspected source says, at the recorded location—bounded by its scope and graded by its confidence. Nothing here is a synthesis across works.

The abstract presents an institutional and governance blueprint through which tax authorities and financial-intelligence units could train federated risk models without exchanging raw taxpayer or transaction data.

confidence: high ssrn-abstract-page apw-e1-ssrn-backfill

Scope: abstract-level cross-jurisdiction institutional design

The proposed design combines federated learning, federated graph models, privacy technologies, a legal blueprint, specified compliance use cases, and a six-month pilot for a small multi-jurisdiction consortium.

confidence: high ssrn-abstract-page apw-e1-ssrn-backfill

Scope: abstract-level architecture and governance proposal; real-world pilot not yet completed

At inspection time, the public Organizations & Markets: Formal & Informal Structures all-years search for artificial intelligence displayed this work among 50 postings.

confidence: high ssrn-ejournal-listing apw-e1-ssrn-backfill

Scope: universe: filtered O&M Formal & Informal Structures listing; unit: posting; period: all years through 2026-08-20; denominator: 50 displayed postings

Structured relationships

In-corpus citations

Only source-supplied cites relationships whose two endpoints are admitted are shown. Invocation evidence remains a separate relationship.

Cites (0)

No in-corpus outgoing citation is available in the current enrichment coverage.

Cited by (0)

No in-corpus incoming citation is available in the current enrichment coverage.

Boundaries

Limitations & independence

Recorded at coding time, carried with the work forever. A claim without its limits is not evidence.

Recorded limitations

  • Abstract-level evidence only; full text, code, and linked implementation were not inspected and no PDF was downloaded.
  • O&M membership is evidenced by the retained public Formal & Informal Structures listing result. Its result URL is session-contextual and omits the journal_id; the retained bytes display the exact family label, query, and 50-posting denominator.
  • The abstract states that experiments use synthetic or public data and that the core thesis still needs validation in a real-data pilot.
  • The abstract page is all-rights-reserved with no reuse without permission; the record paraphrases only.

Source independence

ssrn-only