pith. sign in
Pith Number

pith:T3XG2TU4

pith:2026:T3XG2TU44B5IPFFBH4TV7O3VG2
not attested not anchored not stored refs pending

Scalable and Verifiable Federated Learning for Cross-Institution Financial Fraud Detection

Nishant Nigam, Prajwal Panth

Dynamic stochastic sharding and linear integrity tags let banks train shared fraud models with linear communication costs and verifiable updates.

arxiv:2604.23437 v2 · 2026-04-25 · cs.CR · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{T3XG2TU44B5IPFFBH4TV7O3VG2}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

DSFL replaces mesh topologies with Dynamic Stochastic Sharding, reducing communication complexity from O(N^2) to O(N m), ... Empirical evaluation on the Credit Card Fraud Detection Dataset (ULB) demonstrates an approximately 33x latency reduction compared to Paillier-based secure aggregation, while maintaining strong resilience under simulated failures.

C2weakest assumption

The assumption that Linear Integrity Tags suffice for integrity without enforcing semantic correctness of updates and that dynamic sharding preserves privacy against gradient inversion attacks, as stated in the abstract's description of the mechanisms.

C3one line summary

DSFL introduces dynamic stochastic sharding and linear integrity tags to reduce federated learning communication from quadratic to linear while enabling verifiable aggregation, achieving 33x lower latency than Paillier on credit card fraud data.

Receipt and verification
First computed 2026-05-20T00:03:12.545038Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

9eee6d4e9ce07a8794a13f275fbb753693f0beb48eaea6d220922b53411a3670

Aliases

arxiv: 2604.23437 · arxiv_version: 2604.23437v2 · doi: 10.48550/arxiv.2604.23437 · pith_short_12: T3XG2TU44B5I · pith_short_16: T3XG2TU44B5IPFFB · pith_short_8: T3XG2TU4
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/T3XG2TU44B5IPFFBH4TV7O3VG2 \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 9eee6d4e9ce07a8794a13f275fbb753693f0beb48eaea6d220922b53411a3670
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "7629a3d37f4457154d5cf70c0c779e2cab500b8a69596140f327b01f3761b612",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2026-04-25T20:49:22Z",
    "title_canon_sha256": "ea12dab7173577d9356116d833c3ad48d8fa60af1965a718d84d95eec7822cc2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.23437",
    "kind": "arxiv",
    "version": 2
  }
}