Metraipolis › archive › dc_b6df6603561b

Business Compromise Detection with Agentic AI and LLM-driven Knowledge Discovery — arXiv:2609.32643

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32643
License (as archived)
CC0-1.0
Archived
2026-10-07T20:55:51.208Z
SHA-256 of the archived text
2e79308571b430ad6aa85fcddbc267445d70b8864529be809e1493f1105fc543
Stable URL of this page
https://metraipolis.com/documento/dc_b6df6603561b

How to cite

Business Compromise Detection with Agentic AI and LLM-driven Knowledge Discovery — arXiv:2609.32643 — arXiv (en), https://arxiv.org/abs/2609.32643 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b6df6603561b (Metraipolis archive dc_b6df6603561b, sha256 2e79308571b430ad6aa85fcddbc267445d70b8864529be809e1493f1105fc543)
BibTeX
@misc{dcb6df6603561b,
  title = {Business Compromise Detection with Agentic AI and LLM-driven Knowledge Discovery — arXiv:2609.32643},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32643},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b6df6603561b; sha256 2e79308571b430ad6aa85fcddbc267445d70b8864529be809e1493f1105fc543},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32643. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Detecting compromised business ad accounts is a challenge in digital advertising, as attackers exploit hijacked accounts to launch fraudulent campaigns. Large Language Model (LLM) agents show promise for integrity enforcement, but hallucinated mistakes on hard cases create business friction. In a study we find the autonomous agent is a strong, recall-heavy signal extractor but an unreliable final arbiter, conceding precision on ambiguous decisions. We therefore keep the agent as an investigator that emits a structured, interpretable signal vector, and delegate the verdict to a neuro-symbolic stage: symbolic rules discovered by Inductive Logic Programming (FOIL-IE), a Naïve Bayes calibration layer, and a data-tuned contradiction layer. Evaluating on a compromise-over-sampled population and a realistic low-prevalence sample with subject-matter-expert labels, this arbiter substitution raises MCC from 0.295 to 0.435 ({\Delta}MCC +0.139, 95% CI [+0.026, +0.245], p=0.018, paired bootstrap), lifting precision from 0.250 to 0.446 (1.8x) at a recall cost (0.920 to 0.660). Benchmarked under identical conditions, it also edge tree ensembles (0.386).The rules encode domain w labels while remaininginterpretable and auditable.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.32643 — 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 2026-10-07T20:29:00.898Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).