基于指令与描述的文本数据安全业务属性生成机制

李晨皓; 王娜; 刘敖迪

doi:10.11959/j.issn.2096-109x.2024082

您当前的位置：

首页 >

文章列表页 >

基于指令与描述的文本数据安全业务属性生成机制

学术论文 | 更新时间：2025-02-06

- 基于指令与描述的文本数据安全业务属性生成机制
- Instruction and demonstration-based secure service attribute generation mechanism for textual data
- 网络与信息安全学报 2024年10卷第6期页码：81-95
- 作者机构：
  
  信息工程大学，河南郑州 450001
- 作者简介：
  
  [ "李晨皓（1992-），男，贵州贵阳人，信息工程大学硕士生，主要研究方向为访问控制技术和自然语言处理。" ]
  [ "王娜（1980- ），女，山西临汾人，博士，信息工程大学教授，主要研究方向为信息系统安全、大数据和区块链安全。" ]
  [ "刘敖迪（1992-），男，黑龙江伊春人，博士，信息工程大学讲师，主要研究方向为大数据安全。" ]
- 基金信息：
  
  国家自然科学基金(61802436;62102449);河南省重点研发与推广专项;The Key Research and Development and Promotion Program of Henan Province(222102210069)
- DOI：10.11959/j.issn.2096-109x.2024082
  中图分类号： TP391
- 收稿：2024-05-29，
  
  修回：2024-08-12，
  
  纸质出版：2024-12-25
- 稿件说明：
移动端阅览
李晨皓, 王娜, 刘敖迪. 基于指令与描述的文本数据安全业务属性生成机制[J]. 网络与信息安全学报, 2024, 10(6): 81-95.

LI C H, WANG N, LIU A D. Instruction and demonstration-based secure service attribute generation mechanism for textual data[J]. Chinese Journal of Network and Information Security, 2024, 10(6): 81-95.
李晨皓, 王娜, 刘敖迪. 基于指令与描述的文本数据安全业务属性生成机制[J]. 网络与信息安全学报, 2024, 10(6): 81-95. DOI： 10.11959/j.issn.2096-109x.2024082.

LI C H, WANG N, LIU A D. Instruction and demonstration-based secure service attribute generation mechanism for textual data[J]. Chinese Journal of Network and Information Security, 2024, 10(6): 81-95. DOI： 10.11959/j.issn.2096-109x.2024082.

摘要

客体资源的安全业务属性标定是实施基于属性的访问控制机制的基础和关键。传统上，文本数据安全业务属性标定主要依靠人类专家及机器学习的方法，其效率及少样本能力过于低，并且传统方法多以文本数据中的实体作为业务属性，所提取的属性粒度粗糙、规模及安全管控层级均不可控，极易导致属性空间膨胀问题。基于此，提出了一种基于指令与描述的文本数据安全业务属性生成机制（IDSAM

instruction and demonstration-based secure service attribute generation mechanism for textual data）。具体来说，首先将安全业务属性生成中的候选业务属性（即实体）提取任务由序列标定问题转换为可控生成问题，利用指令学习和情境学习技术实现对候选业务属性的提取；然后，利用WordNet实现对候选业务属性的语义泛化及去冗余，同时通过控制余弦相似度阈值的方法避免语义过于泛化带来的语义丢失问题，生成业务属性集；最后，以集合中初始属性与衍生属性间相似度为边权重，构建加权有向无环属性图，实现了能够根据安全管控需求动态生成、规模可控、安全粒度可调的安全业务属性库构建。实验结果表明，所提机制中候选业务属性提取部分功能在CoNLL-2003数据集上的少样本实验中取得的平均

1分数较基线模型更高，并且所提机制能够按照安全管控需求，动态挖掘出安全管控层级可调、规模可控的安全业务属性。

Abstract

Attribute-based access control is fundamentally dependent on the secure service attribute calibration of object sources. Traditionally

the calibration of secure service attribute for textual data has been primarily reliant on human experts and machine learning methods

yet the efficiency and few-shot ability are insufficient. Moreover

traditional approaches have predominantly utilized entities in textual data as service attributes

resulting in coarse granularity

uncontrollable scale and management level

further leading to the problem of attribute-space explosion. Thus

a secure service attribute generation mechanism for textual data (IDSAM) was introduced. This mechanism addressed the aforementioned challenges by transforming the extraction of candidate service attributes

previously a sequence-calibrated problem

into a controllable-generation problem through instruction learning and in-context learning. Subsequently

WordNet was employed to achieve semantic deduplication

and generalization of the candidate service attributes. Concurrently

to prevent semantic loss due to over-generalization

a cosine similarity threshold was regulated

enabling the generation of a service attribute set. Finally

a weighted directed acyclic attribute graph was constructed based on the similarity between initial and derived attributes within the set

facilitating the dynamic construction of a secure service attribute library with a controllable scale and adjustable security granularity

in accordance with security control requirements. The candidate service attribute extraction component of the proposed mechanism achieves an optimal average

1 score in few-shot experiments on the CoNLL-2003 dataset

surpassing the baseline model. This positions the mechanism as state-of-the-art. Furthermore

the mechanism is capable of dynamically mining secure service attributes with adjustable security control levels and controllable scales to meet varying security management requirements. The experimental results indicate that the proposed mechanism is effective in generating secure service attributes with the desired characteristics.

关键词

Keywords

references

房梁 , 殷丽华 , 郭云川 , 等 . 基于属性的访问控制关键技术研究综述 [J ] . 计算机学报 . 2017 ( 40 ): 1680 - 1698 .

FANG L , YIN L H , GUO Y C , et al . A survey of key technologies in attribute-based access control scheme [J ] . Chinese Journal of Computers , 2017 , ( 40 ): 1680 - 1698 .

ALOHALY M , TAKABI H , BLANCO E . A deep learning approach for extracting attributes of abac policies [C ] // Proceedings of the 23nd ACM on Symposium on Access Control Models and Technologies . Indianapolis, Indiana . 2018 : 137 - 148 .

LIU A , DU X , WANG N . Unstructured text resource access control attribute mining technology based on convolutional neural network [J ] . IEEE Access , 2019 , 7 : 43031 - 43041 .

HEAPS J , KRISHNAN R , HUANG Y , et al . Access control policy generation from user stories using machine learning [C ] // 35th Annual IFIP WG 11.3 Conference on Data and Applications Security and Privacy XXXV: (DBSec 2021). 2021 : 171 - 188 .

包乾辉 , 文娟 , 石淑珍 , 等 . 融合句法依存与BERT-Att-BiLSTM的属性分类 [J ] . 北京邮电大学学报 . 2023 ( 46 ): 123 - 128 .

BAO Q H , WEN J , SHI S Z , et al . Aspect category classification integrated in syntactic dependency and BERT-Att-BiLSTM [J ] . Journal of Beijing University of Posts and Telecommunications , 2023 , ( 46 ): 123 - 128 .

WANG L , LI R , YAN Y , et al . Instructionner:a multi-task instruction-based generative framework for few-shot ner [J ] . arXiv: 2203.03903 , 2022 .

LI D , NAN Y , WANG W , et al . Unified language model pre-training for natural language understanding and generation [C ] // Proceedings of the 33rd International Conference on Neural Information Processing Systems . 2019 : 13063 - 13075 .

RADFORD A , NARASIMHAN K , SALIMANS T , et al . Improving language understanding by generative pre-training [R ] . OpenAI Blog , 2018 .

BROWN T B , MANN B , RYDER N , et al . Language models are few-shot learners [C ] // Proceedings of the 34th International Conference on Neural Information Processing Systems . 2020 : 1877 - 1901 .

WEI J , BOSMA M , ZHAO V , et al . Finetuned language models are zero-shot learners [C ] // Proceedings of the 10th International Conference on Learning Representations . 2022 .

LIU A , DU X , WANG N . Efficient access control permission decision engine based on machine learning [J ] . Security and Communication Networks . 2021 , 1 : 11 .

STRAKOVá J , STRAKA M , HAJIC J . Neural architectures for nested NER through linearization [C ] // Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics . 2019 : 5326 - 5331 .

YAN H , DENG B , LI X , et al . TENER: adapting transformer encoder for named entity recognition [J ] . arXiv: 1911.04474 , 2019 .

LIANG C , YU Y , JIANG H , et al . BOND: BERT-assisted open-domain named entity recognition with distant supervision [C ] // The Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . 2020 .

LI X Y , FENG J R , MENG Y X , et al . A unified MRC framework for named entity recognition [C ] // Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics . 2020 : 5849 - 5859 .

YAN H , GUI T , DAI J Q , et al . A unified generative framework for various ner subtasks [C ] // Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing . 2021 : 5808 - 5822 .

CHEN S , NEVES L , SOLORIO T . Style transfer as data augmentation: a case study on named entity recognition [C ] // Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing . 2022 : 1827 - 1841 .

RAFFEL C , SHAZEER N , ROBERTS A , et al . Exploring the limits of transfer learning with a unified text-to-text transformer [J ] . The Journal of Machine Learning Research . 2020 , 21 : 5485 - 5551 .

LEE D H , KADAKIA A , TAN K , et al . Good examples make a faster LEARNER: simple demonstration-based learning for low-resource ner [C ] // Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics . 2022 : 2687 - 2700 .

CHEN J W , LU Y J , LIN H Y , et al . Learning in-context learning for named entity recognition [C ] // Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics . 2023 : 13661 - 13675 .

ZHANG J , LIU X , LAI X , et al . 2INER: instructive and in-context learning on few-shot named entity recognition [C ] // Findings of the Association for Computational Linguistics: EMNLP 2023 . 2023 : 3940 - 3951 .

MILLER G A . WordNet: a lexical database for english [J ] . Commun ACM ， 1995 , 38 : 39 - 41 .

CUI L Y , WU Y , LIU J , et al . Template-based named entity recognition using bart [C ] // Proceeding of Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 . 2021 : 1835 - 1845 .

HOU Y P , ZHANG J J , LIN Z H , et al . Large language models are zero-shot rankers for recommender systems [C ] // Proceedings of the 46th European Conference on Information Retrieval ( ECIR 2024 ). 2024 : 364 - 381 .

FRIEDMAN L , AHUJA S , ALLEN D , et al . Leveraging large language models in conversational recommender systems [J ] . arXiv: 2305.07961 , 2023 .

YANG J , LIANG S L , ZHANG Y . Design challenges and misconceptions in neural sequence labeling [C ] // Proceedings of the 27th International Conference on Computational Linguistics . 2018 : 3879 - 3889 .

LIANG C , YU Y , JIANG H , et al . Bond: Bert-assisted open-domain named entity recognition with distant supervision [C ] // Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . 2020 : 1054 - 1064 .

STRUBELL E , VERGA P , BELANGER D , et al . Fast and accurate entity recognition with iterated dilated convolutions [C ] // The 2017 Conference on Empirical Methods in Natural Language Processing . 2017 : 2670 - 2680 .

CUI L Y , ZHANG Y . Hierarchically-refined label attention network for sequence labeling [C ] // The 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) . 2019 : 4115 - 4128 .

CHEN X , LI L , DENG S M , et al . LightNER: a lightweight tuning paradigm for low-resource ner via pluggable prompting [C ] // Proceedings of the 29th International Conference on Computational Linguistics . 2022 : 2374 - 2387 .

HUANG J , LI C , SUBUDHI K , et al . Few-shot named entity recognition: an empirical baseline study [C ] // Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing . 2021 : 10408 - 10423 .

DEVLIN J , CHANG M W , LEE K , et al . BERT: pre-training of deep bidirectional transformers for language understanding [C ] // Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies . 2019 : 4171 - 4186 .

MA R T , ZHOU X , GUI T , et al . Template-free prompt tuning for few-shot ner [C ] // Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies . 2022 : 5721 - 5732 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

AutoVulnFix: 大语言模型驱动的智能搜索自适应漏洞修复系统

基于隐私集合求交的大模型双向隐私授权

mmDefender: 基于多模态多语言对抗训练的大语言模型增强方法

物联网设备固件自动化漏洞挖掘技术研究综述

“最小必要”原则视角检测移动应用程序的隐私合规性