請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93447完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 林守德 | zh_TW |
| dc.contributor.advisor | Shou-De Lin | en |
| dc.contributor.author | 詹凱傑 | zh_TW |
| dc.contributor.author | Kai-Chieh Chan | en |
| dc.date.accessioned | 2024-08-01T16:10:11Z | - |
| dc.date.available | 2024-08-02 | - |
| dc.date.copyright | 2024-08-01 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-07-30 | - |
| dc.identifier.citation | [1] M. Belkin and P. Niyogi. Laplacian eigenmaps and spectral techniques for em- bedding and clustering. In T. Dietterich, S. Becker, and Z. Ghahramani, editors, Advances in Neural Information Processing Systems, volume 14. MIT Press, 2001.
[2] H. Cai, V. W. Zheng, and K. C.-C. Chang. A comprehensive survey of graph em- bedding: Problems, techniques and applications, 2018. [3] S. Chanpuriya, C. Musco, K. Sotiropoulos, and C. E. Tsourakakis. Deepwalking backwards: From embeddings back to graphs, 2021. [4] A. Continella, M. Polino, M. Pogliani, and S. Zanero. There’s a hole in that bucket!: A large-scale analysis of misconfigured s3 buckets. In ACSAC ’18, page 702– 711. ACM Publishing, Dec. 2018. 34th Annual Computer Security Applications Conference, ACSAC 2018, ACSAC ; Conference date: 03-12-2018 Through 07-12- 2018. [5] V. Duddu, A. Boutet, and V. Shejwalkar. Quantifying privacy leakage in graph embedding. In MobiQuitous 2020 - 17th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous '20. ACM, Dec. 2020. [6] B. Fatemi, L. E. Asri, and S. M. Kazemi. Slaps: Self-supervision improves structure learning for graph neural networks, 2021. [7] M. Fey and J. E. Lenssen. Fast graph representation learning with PyTorch Geo- metric. In ICLR Workshop on Representation Learning on Graphs and Manifolds, 2019. [8] J. Gawlikowski, C. R. N. Tassi, M. Ali, J. Lee, M. Humt, J. Feng, A. Kruspe, R. Triebel, P. Jung, R. Roscher, M. Shahzad, W. Yang, R. Bamler, and X. X. Zhu. A survey of uncertainty in deep neural networks, 2022. [9] P. Goyal and E. Ferrara. Graph embedding techniques, applications, and perfor- mance: A survey. Knowledge-Based Systems, 151:78–94, July 2018. [10] A. Grover and J. Leskovec. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pages 855–864, 2016. [11] W. Hamilton, Z. Ying, and J. Leskovec. Inductive representation learning on large graphs. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vish- wanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017. [12] X. He, R. Wen, Y. Wu, M. Backes, Y. Shen, and Y. Zhang. Node-level membership inference attacks against graph neural networks, 2021. [13] V. Kalofolias. How to learn a graph from smooth signals, 2016. [14] T. N. Kipf and M. Welling. Variational graph auto-encoders, 2016. [15] T. N. Kipf and M. Welling. Semi-supervised classification with graph convolutional networks, 2017. [16] F. T. Liu, K. M. Ting, and Z.-H. Zhou. Isolation forest. In 2008 Eighth IEEE International Conference on Data Mining, pages 413–422, 2008. [17] Y. Liu, Y. Zheng, D. Zhang, H. Chen, H. Peng, and S. Pan. Towards unsupervised deep graph structure learning, 2022. [18] M. Malekzadeh, A. Borovykh, and D. Gündüz. Honest-but-curious nets: Sen- sitive attributes of private inputs can be secretly coded into the classifiers'out-puts. In Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, CCS '21. ACM, Nov. 2021. [19] S. Pan, R. Hu, G. Long, J. Jiang, L. Yao, and C. Zhang. Adversarially regularized graph autoencoder for graph embedding, 2019. [20] X. Pan, M. Zhang, S. Ji, and M. Yang. Privacy risks of general-purpose language models. 2020 IEEE Symposium on Security and Privacy (SP), pages 1314–1331, 2020. [21] A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Köpf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala. Pytorch: An imperative style, high-performance deep learning library, 2019. [22] B. Sanchez-Lengeling, E. Reif, A. Pearce, and A. B. Wiltschko. A gentle introduc- tion to graph neural networks. Distill, 2021. https://distill.pub/2021/gnn-intro. [23] Y. Shen, Y. Han, Z. Zhang, M. Chen, T. Yu, M. Backes, Y. Zhang, and G. Stringhini. Finding mnemon: Reviving memories of node embeddings, 2022. [24] J. Shlens. A tutorial on principal component analysis, 2014. [25] C. Song, T. Ristenpart, and V. Shmatikov. Machine learning models that remember too much, 2017. [26] Y. C. Tsai, C. T. Li, and S. D. Lin. Centrality-based embedding inversion attack on graph embeddings, 2023. [27] P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio. Graph attention networks, 2018. [28] P. Veličković, W. Fedus, W. L. Hamilton, P. Liò, Y. Bengio, and R. D. Hjelm. Deep graph infomax, 2018. [29] X. Wang and W. Wang. Group property inference attacks against graph neural networks. In CCS 2022 - Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, Proceedings of the ACM Conference on Computer and Communications Security, pages 2871–2884, Nov. 2022. Publisher Copyright: © 2022 ACM.; 28th ACM SIGSAC Conference on Computer and Com- munications Security, CCS 2022 ; Conference date: 07-11-2022 Through 11-11- 2022. [30] F. Wu, Y. Long, C. Zhang, and B. Li. Linkteller: Recovering private edges from graph neural networks via influence analysis. In 2022 IEEE Symposium on Security and Privacy (SP), pages 2005–2024, 2022. [31] K. Xu, W. Hu, J. Leskovec, and S. Jegelka. How powerful are graph neural net- works?, 2019. [32] Z. Yang, W. W. Cohen, and R. Salakhutdinov. Revisiting semi-supervised learning with graph embeddings, 2016. [33] Z. Zhang, M. Chen, M. Backes, Y. Shen, and Y. Zhang. Inference attacks against graph neural networks. In 31st USENIX Security Symposium (USENIX Security 22), pages 4543–4560, Boston, MA, Aug. 2022. USENIX Association. [34] W. Zheng, E. W. Huang, N. Rao, Z. Wang, and K. Subbian. You only transfer what you share: Intersection-induced graph transfer learning for link prediction, 2023. [35] Z.Zhou,C.Zhou,X.Li,J.Yao,Q.Yao,andB.Han.Onstrengtheninganddefending graph reconstruction attack with markov chain approximation, 2023. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93447 | - |
| dc.description.abstract | 本文提出了一個針對圖逆推攻擊的方法。針對圖形神經網絡的安全和隱私問 題，提出了一個新的模型，在只需要訪問原始圖的節點嵌入矩陣，而無需與節點 嵌入模型進行交互，也不需要得知原始圖嵌入模型的算法，就可以實現還原原始 圖並獲得相當高的準確度。透過預測節點的連接數以及使用自編碼器來學習圖形 的結構，達到精準的預測原始圖形的結構。並經由實驗，展示了圖形還原攻擊的 有效性和實用性。 | zh_TW |
| dc.description.abstract | The thesis discusses the privacy risks associated with graph embedding models, particularly highlighting the possibility of a graph embedding inversion attack. It introduces a novel graph recovery attack capable of accurately reconstructing graph edges from node embeddings without any interaction with the embedding models or knowledge of the embedding algorithms. This is achieved by predicting node degrees and using an autoencoder to learn the graph’s properties, thus facilitating a precise reconstruction of the original graph. This raises significant privacy concerns. The effectiveness of this attack has been demonstrated through experimental validation. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-08-01T16:10:11Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-08-01T16:10:11Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員會審定書 (i)
誌謝 (ii) 摘要 (iv) Abstract (v) Contents (vi) List of Figures (ix) List of Tables (x) Chapter1 Introduction (1) Chapter2 Related Work (5) 2.1 Related Studies (5) 2.2 Comparison of Related Studies (6) Chapter3 Preliminaries (8) 3.1 Graph Embeddings (8) 3.2 Notation (9) Chapter4 Problem Definition (11) 4.1 Scenario (11) 4.2 Background Information (12) Chapter5 Methodology (13) 5.1 Model Overview (13) 5.2 Feature Extraction (14) 5.2.1 Principal Components Analysis (15) 5.2.2 Top K of Embedding Similarity (15) 5.2.3 Embedding Statistics (16) 5.2.4 Neighbors Threshold (17) 5.2.5 Isolation Forest (17) 5.3 Prediction Model (17) 5.4 Graph Generator (20) 5.5 Graph Refinement (22) 5.5.1 Encoder (23) 5.5.2 Decoder (24) 5.5.3 Loss (24) 5.5.4 Finalize (26) 5.6 Algorithm Overview (27) Chapter6 Experiments (28) 6.1 Experiments Setting (28) 6.1.1 Dataset (30) 6.1.2 Baseline (30) 6.1.3 Evaluation Metrics (31) 6.2 Experiments with Performing Graph Reconstruction Attacks (32) 6.3 Experiments on the Effect of Embedding Size (33) 6.4 Ablation Study (37) 6.4.1 Ablation Study on the Importance of Feature Extraction (38) 6.4.2 Ablation Study on the Importance of Each Feature (39) 6.4.3 Ablation Study on the Importance of Degree Prediction (40) 6.4.4 Ablation Study of Loss in Graph Reconstruction Stage (41) Chapter7 Defense Approach (42) 7.1 Embedding Perturbation (43) Chapter8 Conclusion (45) References (46) | - |
| dc.language.iso | en | - |
| dc.subject | 逆向攻擊 | zh_TW |
| dc.subject | 圖嵌入 | zh_TW |
| dc.subject | 圖自編碼器 | zh_TW |
| dc.subject | 圖生成 | zh_TW |
| dc.subject | 節點重要性 | zh_TW |
| dc.subject | Node Degree | en |
| dc.subject | Graph Generator | en |
| dc.subject | Graph AutoEncoder | en |
| dc.subject | Embedding Inversion Attack | en |
| dc.subject | Graph Embedding | en |
| dc.title | 基於圖節點重要性之圖還原攻擊 | zh_TW |
| dc.title | Node Importance Aware Graph Reconstruction Attack | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 葉彌妍;李政德;陳尚澤 | zh_TW |
| dc.contributor.oralexamcommittee | Mi-Yen Yeh;Cheng-Te Li;Shang-Tse Chen | en |
| dc.subject.keyword | 圖嵌入,逆向攻擊,節點重要性,圖生成,圖自編碼器, | zh_TW |
| dc.subject.keyword | Graph Embedding,Embedding Inversion Attack,Node Degree,Graph Generator,Graph AutoEncoder, | en |
| dc.relation.page | 50 | - |
| dc.identifier.doi | 10.6342/NTU202402525 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-08-01 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf 未授權公開取用 | 2.65 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。