智能体
arxiv.org ·
基于智能体 AI 与 LLM 驱动知识发现的商业账户入侵检测
论文针对数字广告中被劫持商业账户发起欺诈活动的问题，指出 LLM 智能体虽擅长召回但作为最终裁决者不可靠。作者将智能体保留为调查者，输出结构化可解释信号向量，把裁决交给神经符号阶段：由归纳逻辑编程（FOIL-IE）发现的符号规则、朴素贝叶斯校准层和数据调优的矛盾层。在过采样与低流行率专家标注样本上，该仲裁替换使 MCC 从 0.295 升至 0.435（ΔMCC +0.139，95% CI [+0.026,+0.245]，p=0.018），精确率从 0.250 升至 0.446（1.8 倍），召回率从 0.920 降至 0.660，并略优于树集成（0.386）。规则编码领域知识且保持可解释与可审计。
AI推荐理由 arXiv 论文，摘要给出明确实验设置与量化结果：将 LLM 智能体定位为信号提取器而非最终裁决者，改用归纳逻辑编程（FOIL-IE）发现的符号规则加朴素贝叶斯校准与矛盾层，在专家标注的低流行率样本上 MCC 从 0.295 提升至 0.435（95% CI [+0.026,+0.245]，p=0.018），精确率 0.250→0.446，召回率 0.920→0.660，并优于树集成（0.386）。新信息在于智能体+神经符号仲裁的架构取舍与可审计规则，对 Agent 落地与风控应用有参考价值；局限是召回率明显下降、样本为过采样与特定广告账户场景，泛化性未验证。
72
正文
Computer Science > Artificial Intelligence
arXiv:2609.32643 (cs)
[Submitted on 26 Sep 2026]
Title:Business Compromise Detection with Agentic AI and LLM-driven Knowledge Discovery
Authors:Diego Palma, Kyu Bin Kim, Zhen Han, Allbright Dsouza, Zhiyuan Liu
View a PDF of the paper titled Business Compromise Detection with Agentic AI and LLM-driven Knowledge Discovery, by Diego Palma and 4 other authors
View PDF
HTML (experimental)
Abstract: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.
Comments:
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.32643 [cs.AI]
(or
arXiv:2609.32643v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.32643
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Diego Palma [view email]
[v1]
Sat, 26 Sep 2026 14:05:25 UTC (109 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Business Compromise Detection with Agentic AI and LLM-driven Knowledge Discovery, by Diego Palma and 4 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)