{
  "abstract": "Machine learning-based credit scoring is increasingly central to Peer-to-Peer (P2P) lending, yet its resilience to adversarial manipulation, where applicants strategically alter self-reported inputs to secure favourable decisions, remains poorly understood. Most adversarial-robustness evidence comes from image and text domains and evaluates a single attack against a matching defence, offering little guidance on how defences generalise across attack types in tabular credit data. We address this with a systematic train-test robustness benchmark on a large Lending Club subset, spanning three model families (logistic regression, a feed-forward neural network, and a transformer for tabular data) and four attacks confined to applicant-mutable features: Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), Salt-and-Pepper (S&P) noise, and DeepFool, plus a mixed-attack regime. Across a full grid evaluated with stratified cross-validation, adversarial training sharply improves robustness against the attack it is trained on and transfers well within the gradient-based family, but transfers weakly to non-gradient corruption, so single-attack defences overstate real-world resilience. Mixed training delivers the most balanced robustness across heterogeneous attacks while preserving clean-test performance, supporting multi-attack stress testing in credit-model governance.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.09945",
  "author_total": 4,
  "authors": [
    {
      "name": "Gijs A. F. Niewzwaag"
    },
    {
      "name": "Marijn G. S. Veth"
    },
    {
      "name": "Manuele Massei"
    },
    {
      "name": "Marcos R. Machado"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/af93fved3bg7f.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.09945",
  "fulltext_url": null,
  "id": "af93fved3bg7f",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.09945",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-fin.RM"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Adversarial Robustness in Machine Learning"
    ]
  ],
  "openalex": "W7212169596",
  "pdf_url": "https://arxiv.org/pdf/2609.09945",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-09",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/af93fved3bg7f.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:22Z",
      "native_id": "2609.09945",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.09945"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Adversarial Training for Tabular Credit Scoring: A Multi-Attack Robustness Evaluation in P2P Lending",
  "title_text": "Adversarial Training for Tabular Credit Scoring: A Multi-Attack Robustness Evaluation in P2P Lending",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:22Z",
  "url": "https://research.draconitic.com/paper/af93fved3bg7f",
  "venue": "arXiv",
  "versions": []
}