|
|
知识图谱嵌入的安全性问题分析
|
Abstract:
知识图谱作为新型数据语义分析模型得到广泛应用，人们对提交数据安全的需求也日益提高。为帮助目前面临的数据孤岛和关联网络构建问题，知识图谱得到了现有研究中的广泛关注和研究。虽然知识图谱作为一种极具影响的机器学习技术，能够对离散数据进行关联关系挖掘分析，但是也存在很多安全性问题。因此本文对知识图谱构建过程中面临的隐私安全隐患进行总结和分析，这对知识图谱的发展及应用具有重要意义，本文首先对知识图谱的基本概念和知识图谱嵌入过程进行详细阐述；接着，深入分析知识图谱建模过程中遇到的隐私泄露问题，包括模型逆向攻击、模型萃取攻击、投毒共计。然后，归纳总结了不同的知识图谱嵌入过程中的攻击防御方法。最后，总结与展望了知识图谱嵌入的应用前景及未来重要研究方向。
Crowd sensing, as a new data collection mode, has been widely applied, and people’s demand for submitting data security is also increasing. In the multi-participant joint construction of graph models, there are many privacy and security risks. Therefore, this article summarizes and analyzes the privacy and security risks faced in the process of constructing knowledge graphs, which is of great significance for the development and application of knowledge graphs. Firstly, this article elaborates on the basic concepts of knowledge graphs and the embedding process of knowledge graphs in detail; Next, an in-depth analysis will be conducted on the privacy leakage issues encountered in the process of knowledge graph modeling, including. Then, the privacy protection methods in different knowledge graph embedding processes were summarized and summarized. Finally, the application prospects and important future research directions of knowledge graph embedding were summarized and prospected.
| [1] | Jain, N. (2020) Domain-Specific Knowledge Graph Construction for Semantic Analysis. In: Harth, A., et al., Eds., The Semantic Web: ESWC 2020 Satellite Events, Springer, Cham, 250-260. https://doi.org/10.1007/978-3-030-62327-2_40 |
| [2] | Zhang, L., He, Q., Yu, W., et al. (2022) Research on Entity Disambiguation Method and Model Construction Based on Knowledge Graph. 2022 4th International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), Shanghai, 28-30 October 2022, 174-177. https://doi.org/10.1109/MLBDBI58171.2022.00041 |
| [3] | Wei, L., Zhao, H. and He, Z. (2022) Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective. Proceedings of the ACM Web Conference 2022, Nanjing, 25-29 April 2022, 1381-1391.
https://doi.org/10.1145/3485447.3512185 |
| [4] | Omar, R., Mangukiya, O., Kalnis, P., et al. (2023) ChatGPT versus Traditional Question Answering for Knowledge Graphs: Current Status and Future Directions towards Knowledge Graph Chatbots. arXiv: 2302.06466.
https://doi.org/10.1145/3588911 |
| [5] | Bordes, A., Usunier, N., Garcia-Duran, A., et al. (2013) Translating Embeddings for Modeling Multi-Relational Data. Advances in Neural Information Processing Systems, 26, 2787-2795. |
| [6] | He, X., Wen, R., Wu, Y., et al. (2021) Node-Level Membership Inference Attacks against Graph Neural Networks. arXiv: 2102.05429. |
| [7] | Wu, B., Yang, X., Pan, S., et al. (2022) Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realisation. Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security, Nagasaki, 30 May-3 June 2022, 337-350. https://doi.org/10.1145/3488932.3497753 |
| [8] | Zhang, Z., Liu, Q., Huang, Z., et al. (2021) GraphMi: Extracting Private Graph Data from Graph Neural Networks. Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21). Montreal, 19-27 August 2021, 3749-3755. https://doi.org/10.24963/ijcai.2021/516 |
| [9] | Wu, H., Wang, C., Tyshetskiy, Y., et al. (2019) Adversarial Examples on Graph Data: Deep Insights into Attack and Defense. arXiv: 1903.01610. https://doi.org/10.24963/ijcai.2019/669 |
| [10] | Entezari, N., Al-Sayouri, S.A., Darvishzadeh, A., et al. (2020) All You Need Is Low (Rank) Defending against Adversarial Attacks on Graphs. Proceedings of the 13th International Conference on Web Search and Data Mining, Houston, 3-7 February 2020, 169-177. https://doi.org/10.1145/3336191.3371789 |
| [11] | Liu, N., Yang, H. and Hu, X. (2018) Adversarial Detection with Model Interpretation. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, 19-23 August 2018, 1803-1811.
https://doi.org/10.1145/3219819.3220027 |
| [12] | Feng, F., He, X., Tang, J., et al. (2019) Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure. IEEE Transactions on Knowledge and Data Engineering, 33, 2493-2504.
https://doi.org/10.1109/TKDE.2019.2957786 |
| [13] | Li, J., Peng, J., Chen, L., et al. (2022) Spectral Adversarial Training for Robust Graph Neural Network. IEEE Transactions on Knowledge and Data Engineering, 35, 9240-9253. https://doi.org/10.1109/TKDE.2022.3222207 |
| [14] | Zhang, Z., Jia, J., Wang, B., et al. (2021) Backdoor Attacks to Graph Neural Networks. Proceedings of the 26th ACM Symposium on Access Control Models and Technologies, New York, 16-18 June 2021, 15-26.
https://doi.org/10.1145/3450569.3463560 |
