网络与信息安全学报 ›› 2023, Vol. 9 ›› Issue (2): 164-174.doi: 10.11959/j.issn.2096-109x.2023030

• 学术论文 • 上一篇    下一篇

人工智能安全知识图谱构建技术研究

沈晓晨1, 葛寅辉1, 陈波1, 于泠2   

  1. 1 南京师范大学计算机与电子信息学院/人工智能学院，江苏 南京 210023
    2 南京师范大学数学科学学院，江苏 南京 210023
  • 修回日期:2022-12-25 出版日期:2023-04-25 发布日期:2023-04-01
  • 作者简介:沈晓晨（1998- ），女，山东济宁人，南京师范大学硕士生，主要研究方向为人工智能安全、知识图谱
    葛寅辉（1998- ），男，江苏扬州人，南京师范大学硕士生，主要研究方向为人工智能安全
    陈波（1972- ），男，江苏南通人，博士，南京师范大学教授，主要研究方向为人工智能安全和智慧教育
    于泠（1971- ），女，江苏常州人，博士，南京师范大学副教授，主要研究方向为网络空间安全和智慧教育
  • 基金资助:
    教育部科技司赛尔网络下一代互联网技术创新项目滚动项目(NGIICS20190504);江苏省“十四五”教育科学规划重大课题(A/2021/05)

Research on construction technology of artificial intelligence security knowledge graph

Xiaochen SHEN1, Yinhui GE1, Bo CHEN1, Ling YU2   

  1. 1 School of Computer and Electronic Information/School of Artificial Intelligence, Nanjing Normal University, Nanjing 210023, China
    2 School of Mathematical Science, Nanjing Normal University, Nanjing 210023, China
  • Revised:2022-12-25 Online:2023-04-25 Published:2023-04-01
  • Supported by:
    The CERNET Next Generation Internet Technology Innovation Project under the Ministry of Education’s Science and Technology Department(NGIICS20190504);The Education Scientific Planning Project of Jiangsu Province during the “14th Five-Year Plan”(A/2021/05)

在线阅读

55

pdf下载

545

摘要：

人工智能技术在飞速发展的同时引发众多安全隐患，现阶段人工智能安全数据来源广泛、种类复杂并且缺乏规范描述，为此提出了一种人工智能安全知识图谱构建方法，利用知识图谱对当前多源异构数据进行分析与整合，将复杂关联的数据进行科学表示，挖掘潜在价值并形成领域知识库。针对人工智能安全领域概念的多样性和关联性，提出一种分层结构人工智能安全本体，使本体结构更加多元化和扩展化，为知识图谱构建过程提供规则约束，并基于此形成人工智能安全知识库；为了有效利用特征信息及减少噪声干扰，采取基于双向长短时记忆网络-条件随机场（BiLSTM-CRF）的命名实体识别算法和基于卷积神经网络-注意力机制（CNN-ATT）的关系抽取算法进行信息抽取，利用构建的人工智能安全数据集证明算法性能；以提出的安全本体为知识体系，以3D效果展现人工智能安全知识图谱多层次可视化结果，有效关联多源安全数据信息。实验结果表明，信息抽取算法性能良好，取得了比传统方法更好的效果；构建的人工智能安全知识图谱直观展示了层次结构及相互关系，符合准确性、一致性、完整性、时效性维度的知识图谱多维度评估标准，能够为人工智能安全研究提供支持。

关键词: 人工智能安全, 知识图谱, 本体构建, 信息抽取, 可视化

Abstract:

As a major strategic technology, artificial intelligence is developing rapidly while bringing numerous security risks.Currently, security data for artificial intelligence is collected from disparate sources and lacks standardized description, making it difficult to integrate and analyze effectively.To address this issue, a method for constructing an artificial intelligence security knowledge graph was proposed.The knowledge graph was used to integrate the current multi-source heterogeneous data, scientifically represent complex relationships of the data, mine potential value and form a domain knowledge base.In view of the diversity and correlation of concepts in the field of artificial intelligence security, a hierarchical structure of artificial intelligence security ontology was proposed to make the ontology structure more diversified and extensible, provide rule constraints for the process of knowledge graph construction, and form an artificial intelligence security knowledge base.To effectively utilize feature information and reduce noise interference, named entity recognition algorithm based on BiLSTM-CRF and relationship extraction algorithm based on CNN-ATT were adopted for information extraction.The constructed artificial intelligence security dataset was then used to verify the performance of the algorithm.Based on the proposed ontology, the multi-level visualization results of the artificial intelligence security knowledge graph were presented in 3D effect, effectively connecting the multi-source security data information.The experimental results show that the constructed knowledge graph meets the multi-dimensional evaluation criteria of accuracy, consistency, completeness, and timeliness, providing knowledge support for artificial intelligence security research.Overall, the proposed method can help address the complexity and heterogeneity of security data in artificial intelligence and provide a more standardized, integrated approach to knowledge representation and analysis.

Key words: artificial intelligence security, knowledge graph, ontology construction, information extraction, visualization

中图分类号: 

No Suggested Reading articles found!