Metraipolis › archive › dc_0f8fe34f7dce

FraudBench: Protocol-Sensitive Benchmarking of Adversarial Robustness for Financial Risk Assessment — arXiv:2608.24551

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.24551
License (as archived)
CC0-1.0
Archived
2026-10-18T06:36:17.031Z
SHA-256 of the archived text
4923b76de38721c09eedc61b7f2a1f6326aad3889d086c7b15f52a227f64faf1
Stable URL of this page
https://metraipolis.com/documento/dc_0f8fe34f7dce

How to cite

FraudBench: Protocol-Sensitive Benchmarking of Adversarial Robustness for Financial Risk Assessment — arXiv:2608.24551 — arXiv (en), https://arxiv.org/abs/2608.24551 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f8fe34f7dce (Metraipolis archive dc_0f8fe34f7dce, sha256 4923b76de38721c09eedc61b7f2a1f6326aad3889d086c7b15f52a227f64faf1)
BibTeX
@misc{dc0f8fe34f7dce,
  title = {FraudBench: Protocol-Sensitive Benchmarking of Adversarial Robustness for Financial Risk Assessment — arXiv:2608.24551},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.24551},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f8fe34f7dce; sha256 4923b76de38721c09eedc61b7f2a1f6326aad3889d086c7b15f52a227f64faf1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24551. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Machine learning models are widely used in financial fraud and credit-risk detection, yet their adversarial robustness remains difficult to evaluate because financial tabular data involve domain-specific constraints, severe class imbalance, and asymmetric attacker capability. We argue that, in this setting, robustness is not only an attribute of the model, but also an attribute of the evaluation protocol. Different ways of enforcing constraints and capability can lead to substantially different robustness conclusions. This paper presents FraudBench, a protocol-sensitive benchmark for adversarial robustness evaluation in financial fraud and credit-risk detection. Rather than treating domain constraints as post-hoc validity checks, FraudBench evaluates the same dataset--model--attack--defence setting under three matched protocols: unconstrained attacks, post-hoc feasibility filtering, and deployment-aware constraint-integrated attacks. FraudBench covers four public financial datasets, and evaluates neural, tree-based, and ensemble models using three attack settings. Our results show that robustness conclusions are highly protocol-sensitive. On Lending Club Loan Data under the white-box setting, post-hoc filtering leaves only 3.7 feasible-flipped examples on average, whereas in-attack projection with attacker mutability masking produces 2,832.3 feasible-flipped examples under the same perturbation budget. The results on IEEE-CIS further show that feasibility and attacker capability are separate axes, while black-box evaluation shows that protocol choice can alter model-family rankings. These findings suggest that fraud robustness evaluation should report predictive degradation and attack feasibility jointly, and should incorporate domain constraints into attack generation rather than treating them as post-processing checks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.24551 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T06:28:52.257Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).