Secure and Explainable Fraud Detection in Finance via Hierarchical Multi-source Dataset Distillation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918264021450752 |
|---|---|
| author | Qian, Yiming Neumann, Thorsten Huang, Xueyining Hardoon, David Gao, Fei Liu, Yong Goh, Siow Mong Rick |
| author_facet | Qian, Yiming Neumann, Thorsten Huang, Xueyining Hardoon, David Gao, Fei Liu, Yong Goh, Siow Mong Rick |
| contents | We propose an explainable, privacy-preserving dataset distillation framework for collaborative financial fraud detection. A trained random forest is converted into transparent, axis-aligned rule regions (leaf hyperrectangles), and synthetic transactions are generated by uniformly sampling within each region. This produces a compact, auditable surrogate dataset that preserves local feature interactions without exposing sensitive original records. The rule regions also support explainability: aggregated rule statistics (for example, support and lift) describe global patterns, while assigning each case to its generating region gives concise human-readable rationales and calibrated uncertainty based on tree-vote disagreement.
On the IEEE-CIS fraud dataset (590k transactions across three institution-like clusters), distilled datasets reduce data volume by 85% to 93% (often under 15% of the original) while maintaining competitive precision and micro-F1, with only a modest AUC drop. Sharing and augmenting with synthesized data across institutions improves cross-cluster precision, recall, and AUC. Real vs. synthesized structure remains highly similar (over 93% by nearest-neighbor cosine analysis). Membership-inference attacks perform at chance level (about 0.50) when distinguishing training from hold-out records, suggesting low memorization risk. Removing high-uncertainty synthetic points using disagreement scores further boosts AUC (up to 0.687) and improves calibration. Sensitivity tests show weak dependence on the distillation ratio (AUC about 0.641 to 0.645 from 6% to 60%).
Overall, tree-region distillation enables trustworthy, deployable fraud analytics with interpretable global rules, per-case rationales with quantified uncertainty, and strong privacy properties suitable for multi-institution settings and regulatory audit. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_21866 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Secure and Explainable Fraud Detection in Finance via Hierarchical Multi-source Dataset Distillation Qian, Yiming Neumann, Thorsten Huang, Xueyining Hardoon, David Gao, Fei Liu, Yong Goh, Siow Mong Rick Machine Learning Artificial Intelligence We propose an explainable, privacy-preserving dataset distillation framework for collaborative financial fraud detection. A trained random forest is converted into transparent, axis-aligned rule regions (leaf hyperrectangles), and synthetic transactions are generated by uniformly sampling within each region. This produces a compact, auditable surrogate dataset that preserves local feature interactions without exposing sensitive original records. The rule regions also support explainability: aggregated rule statistics (for example, support and lift) describe global patterns, while assigning each case to its generating region gives concise human-readable rationales and calibrated uncertainty based on tree-vote disagreement. On the IEEE-CIS fraud dataset (590k transactions across three institution-like clusters), distilled datasets reduce data volume by 85% to 93% (often under 15% of the original) while maintaining competitive precision and micro-F1, with only a modest AUC drop. Sharing and augmenting with synthesized data across institutions improves cross-cluster precision, recall, and AUC. Real vs. synthesized structure remains highly similar (over 93% by nearest-neighbor cosine analysis). Membership-inference attacks perform at chance level (about 0.50) when distinguishing training from hold-out records, suggesting low memorization risk. Removing high-uncertainty synthetic points using disagreement scores further boosts AUC (up to 0.687) and improves calibration. Sensitivity tests show weak dependence on the distillation ratio (AUC about 0.641 to 0.645 from 6% to 60%). Overall, tree-region distillation enables trustworthy, deployable fraud analytics with interpretable global rules, per-case rationales with quantified uncertainty, and strong privacy properties suitable for multi-institution settings and regulatory audit. |
| title | Secure and Explainable Fraud Detection in Finance via Hierarchical Multi-source Dataset Distillation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2512.21866 |