大模型
arxiv.org ·
面向 AI 增强网络安全软件需求生成的大语言模型集成
该 arXiv 预印本研究将 LLM 生成安全需求时的随机性视为资源，提出后生成融合策略：Uniform 融合奖励跨运行一致性，Naive-Bayes 融合按估计可靠性加权。在 12 种配置、24 次运行、4 个模型家族上，针对 10 项 ISO/IEC 27002:2022 控制项生成需求，并以 72 条有效需求为金标准由专家评判。结果显示，融合可将有效需求排在幻觉之前，PR-AUC 与 ROC-AUC 分别达 0.864 和 0.869，优于最佳单配置；内部验证显示增益在至少 92% 的 bootstrap 重采样中保持正向。作者称该轻量层可仅用非前沿模型提升分析师覆盖与审查排序效率。
AI推荐理由 arXiv 论文，来源可信，摘要给出明确方法（后生成融合、Uniform 与 Naive-Bayes 融合）、实验规模（12 种配置、24 次运行、4 个模型家族、10 项 ISO/IEC 27002:2022 控制项、72 条有效需求金标准）与量化结果（AUC 达 0.864/0.869，内部验证在至少 92% 的 bootstrap 重采样中保持正向），信息密度高；局限是仅针对网络安全需求生成这一细分任务，且为预印本、未经同行评审。
78
正文
Computer Science > Software Engineering
arXiv:2609.10316 (cs)
[Submitted on 9 Sep 2026]
Title:Ensembling LLMs for AI-Augmented Cybersecurity Software Requirements Generation
Authors:Santiago Perez-Acuna, Yod-Samuel Martín, Juan C. Yelmo
View a PDF of the paper titled Ensembling LLMs for AI-Augmented Cybersecurity Software Requirements Generation, by Santiago Perez-Acuna and 1 other authors
View PDF
HTML (experimental)
Abstract:Translating high-level controls from security standards into concrete, system-specific requirements is central to cybersecurity requirements engineering. Large language models (LLMs) can accelerate this labor-intensive, recall-sensitive task, but any single run is unreliable: it misses valid safeguards while introducing plausible hallucinations, and outputs shift across runs and models. We reframe this variability as a resource: rather than selecting one output, we study post-generation ensembling, aggregating stochastic runs with information-retrieval data-fusion operators. We propose two strategies: Uniform fusion rewards mere cross-run agreement, whereas Naive-Bayes fusion weights each run by its estimated reliability. We evaluate both over 24 runs from 12 configurations across four model families, generated for ten ISO/IEC 27002:2022 controls and expert-judged against a gold standard of 72 valid requirements. Pooling every run's output recovers all 72 (whereas single configurations recover on average under half) but also 111 hallucinations. Fusion separates the wheat from the chaff, ranking valid requirements well ahead of hallucinations. In the areas under the precision-recall and ROC curves, Uniform fusion alone largely surpasses every original run and configuration by 0.142 and 0.118 over the best configuration. Naive-Bayes weighting adds a further 0.039 and 0.052, reaching 0.864 and 0.869 while attaining useful operating points earlier. Internal validation confirms the stability of these gains: they stay positive in at least 92% of out-of-bag bootstrap resamples and every structured-perturbation sample. Post-generation fusion thus turns apparent noise into a practical asset: a lightweight layer giving analysts broader coverage and a better prioritized review queue, using affordable, below-frontier models alone.
Comments:
Subjects:
Software Engineering (cs.SE)
MSC classes:
68N30 (Primary), 68M25 (Secondary), 68P20, 68T50, 68T20, 68T37
ACM classes:
D.2.1; K.6.5; H.3.3; I.2.7
Cite as:
arXiv:2609.10316 [cs.SE]
(or
arXiv:2609.10316v1 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2609.10316
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Santiago Perez-Acuna [view email]
[v1]
Wed, 9 Sep 2026 15:22:20 UTC (4,496 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Ensembling LLMs for AI-Augmented Cybersecurity Software Requirements Generation, by Santiago Perez-Acuna and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.SE
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?)