# Business Compromise Detection with Agentic AI and LLM-driven Knowledge Discovery

arXiv: https://arxiv.org/abs/2609.32643 · HTML: https://mlsanity.com/paper/2609.32643/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 27 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 6 of 6)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Learning Explanatory Rules from Noisy Data](https://mlsanity.com/paper/1711.04574/) (2017)
- [The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies](https://mlsanity.com/paper/2407.19354/) (2024)
- [Inductive logic programming at 30: a new introduction](https://mlsanity.com/paper/2008.07912/) (2020)
- [Hinge-Loss Markov Random Fields and Probabilistic Soft Logic](https://mlsanity.com/paper/1505.04406/) (2015)
- [Differentiable Inductive Logic Programming for Fraud Detection](https://mlsanity.com/paper/2410.21928/) (2024)

## Abstract (arXiv)

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 Na"ive 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 (DeltaMCC +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.