Open Access

ARTICLE

HiFraud: Hierarchical Privacy-Preserving Federated Learning with Star-Chain Knowledge Transfer for Cross-Institutional Fraud Detection

Zhihao Zhang^1,#, Zhuodong Liu^1,#, Xiangyu Li², Lei Zhang^1,*

1 School of Economics and Management, Beijing Jiaotong University, Beijing, China
2 Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China

* Corresponding Author: Lei Zhang. Email:
# These authors contributed equally to this work

(This article belongs to the Special Issue: Recent Advances in Malware Detection)

Computers, Materials & Continua 2026, 88(2), 34 https://doi.org/10.32604/cmc.2026.081922

Received 11 March 2026; Accepted 13 April 2026; Issue published 15 June 2026

Abstract

Financial fraud detection across institutions faces a fundamental tension between the need for diverse training data and regulatory prohibitions on sharing sensitive records. Existing federated learning approaches suffer from performance degradation under non-IID distributions and substantial utility losses when uniform differential privacy is applied to inherently sparse fraud signals. To this end, this paper proposes HiFraud, a hierarchical federated framework featuring three key components: fraud-aware dynamic clustering with complementarity regularization to group institutions by fraud pattern similarity while preserving rare-type representation; star-chain knowledge transfer augmented by not-true-class distillation to propagate novel fraud patterns rapidly within clusters while mitigating catastrophic forgetting; and privacy-adaptive aggregation via Rényi differential privacy composition, calibrating noise intensity to distributional divergence and fraud rarity. Experiments on IEEE-CIS, PaySim, and Worldline datasets show that HiFraud achieves an area under the receiver operating characteristic curve (AUC-ROC) of 0.935 under ε=2.3, outperforming DP-FedAvg by 10.5% while reducing convergence from 49 to 30 rounds. The framework also suppresses membership inference attack success to 10.2%, detects emerging fraud patterns within 3 h inside clusters, and improves rare fraud type detection by 23.0% over uniform privacy baselines. These results demonstrate that hierarchical architectures can effectively reconcile detection performance, formal privacy guarantees, and rapid threat response in collaborative fraud detection.

---

Keywords

---