大模型
arxiv.org ·
大语言模型安全知识缺口的半自动化检测
该论文提出一种半自动化方法评估 LLM 在特定安全领域的知识水平：以消费者保护机构（CPA）的权威信息为基准，通过检测模型回答的不稳定性来指示知识缺口。作者在身份盗用和冒充诈骗两个主题上，使用 6 家 CPA 的公开信息，对 Gemini 和 GPT 两个模型家族的 5 个模型进行演示，结果显示该方法能区分知识充足与不足的模型。
AI推荐理由 arXiv 论文（cs.CR/cs.AI/cs.HC），作者与提交历史明确，方法描述具体：利用消费者保护机构（CPA）的权威信息，通过 LLM 回答的不稳定性来半自动识别安全知识缺口，并在身份盗用与冒充诈骗两个主题、Gemini 与 GPT 两个模型家族的 5 个模型上做了演示。属于可复现的评测方法学贡献，对 LLM 安全评测有实际参考价值；局限是仅覆盖两个安全主题、依赖 CPA 公开信息，摘要未给出量化结果，且为预印本未经同行评审。
72
正文
Computer Science > Cryptography and Security
arXiv:2607.18496 (cs)
[Submitted on 20 Jul 2026 (v1), last revised 22 Sep 2026 (this version, v4)]
Title:Semi-Automated Detection of Gaps in LLM Security Knowledge
Authors:Shufan Chai, Liangliang Sun, Jessica Staddon
View a PDF of the paper titled Semi-Automated Detection of Gaps in LLM Security Knowledge, by Shufan Chai and 2 other authors
View PDF
HTML (experimental)
Abstract:Large language models (LLMs) are increasingly used for a range of software, hardware and human-centered security tasks. Consequently, LLM performance on security tasks is an active area of measurement and research, often with a focus on identifying areas in which LLM security "knowledge" may be insufficient. Popular strategies for identifying LLM security knowledge gaps include building corpora of challenge questions or task benchmarks, strategies that require substantial manual work and security expertise to design and execute. We introduce a partially-automated method for assessing LLM knowledge of a security area. The method uses authoritative information from Consumer Protection Agencies (CPAs) to identify instability in LLM responses that can be indicative of knowledge gaps. We demonstrate the method for 2 security topics, identity theft and impostor scams, and 5 LLMs in 2 leading LLM families, Gemini and GPT, using publicly available information about identity theft and impostor scams from 6 CPAs. The method distinguishes between models that have and don't have sufficient knowledge to accurately identify the security topics in text narratives.
Comments:
Subjects:
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
Cite as:
arXiv:2607.18496 [cs.CR]
(or
arXiv:2607.18496v4 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2607.18496
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Jessica Staddon [view email]
[v1]
Mon, 20 Jul 2026 20:37:37 UTC (1,003 KB)
[v2]
Wed, 22 Jul 2026 19:09:23 UTC (693 KB)
[v3]
Wed, 29 Jul 2026 16:59:29 UTC (693 KB)
[v4]
Tue, 22 Sep 2026 15:55:40 UTC (694 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Semi-Automated Detection of Gaps in LLM Security Knowledge, by Shufan Chai and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CR
new
|
recent
| 2026-07
Change to browse by:
cs
cs.AI
cs.HC
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?)