《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (8): 2483-2492.DOI: 10.11772/j.issn.1001-9081.2023081110
收稿日期:
2023-08-20
修回日期:
2023-11-01
接受日期:
2023-11-03
发布日期:
2023-12-18
出版日期:
2024-08-10
通讯作者:
郝晓燕
作者简介:
杨莹(1999—),女,山西太原人,硕士研究生,CCF会员,主要研究方向:人工智能安全基金资助:
Ying YANG, Xiaoyan HAO(), Dan YU, Yao MA, Yongle CHEN
Received:
2023-08-20
Revised:
2023-11-01
Accepted:
2023-11-03
Online:
2023-12-18
Published:
2024-08-10
Contact:
Xiaoyan HAO
About author:
bio graphy:YANG Ying, born in 1999, M. S. candidate. Her research interests include artificial intelligence security.Supported by:
摘要:
无数据模型提取攻击是基于攻击者在进行攻击时所需的训练数据信息未知的情况下提出的一类机器学习安全问题。针对无数据模型提取攻击在图神经网络(GNN)领域的研究缺乏,提出分别用GNN可解释性方法GNNExplainer和图数据增强方法GAUG-M优化图节点特征信息和边信息生成所需图数据,最终提取GNN模型的方法。首先,利用GNNExplainer方法对目标模型的响应结果进行可解释性分析得到重要的图节点特征信息;其次,通过对重要的图节点特征加权,对非重要图节点特征降权,实现图节点特征信息的整体优化;然后,使用图形自动编码器作为边信息预测模块,根据优化后的图节点特征得到节点与节点之间的连接概率;最后,根据概率增加或者删减相应边优化边信息。实验采用5个图数据集训练的3种GNN模型架构作为目标模型提取攻击,得到的替代模型达到了73%~87%的节点分类任务准确性和76%~89%的与目标模型性能的一致性,验证了所提方法的有效性。
中图分类号:
杨莹, 郝晓燕, 于丹, 马垚, 陈永乐. 面向图神经网络模型提取攻击的图数据生成方法[J]. 计算机应用, 2024, 44(8): 2483-2492.
Ying YANG, Xiaoyan HAO, Dan YU, Yao MA, Yongle CHEN. Graph data generation approach for graph neural network model extraction attacks[J]. Journal of Computer Applications, 2024, 44(8): 2483-2492.
变量符号 | 含义 |
---|---|
图的基本表示 | |
图中的某个节点表示 | |
节点 | |
节点 | |
节点集合 | |
边集合 | |
节点特征向量 | |
节点标签集合 | |
优化后的图数据 | |
优化后的节点数据 | |
优化后的边数据 | |
优化后的节点特征向量 | |
Mg | 目标模型 |
Ms | 替代模型 |
R | 目标模型的响应结果 |
替代模型的响应结果 |
表1 相关符号表示及解释
Tab. 1 Related symbols and explanations
变量符号 | 含义 |
---|---|
图的基本表示 | |
图中的某个节点表示 | |
节点 | |
节点 | |
节点集合 | |
边集合 | |
节点特征向量 | |
节点标签集合 | |
优化后的图数据 | |
优化后的节点数据 | |
优化后的边数据 | |
优化后的节点特征向量 | |
Mg | 目标模型 |
Ms | 替代模型 |
R | 目标模型的响应结果 |
替代模型的响应结果 |
数据集 | 节点数 | 边数 | 特征向量维度 | 标签数 |
---|---|---|---|---|
DBLP | 17 716 | 105 734 | 1 639 | 4 |
PubMed | 19 717 | 88 648 | 500 | 3 |
Citeseer | 4 230 | 5 358 | 602 | 6 |
ACM | 3 025 | 26 256 | 1 870 | 3 |
Coauthor | 34 493 | 495 924 | 8 415 | 5 |
表2 五个图数据集的节点和边信息
Tab. 2 Node and edge information for five graph datasets
数据集 | 节点数 | 边数 | 特征向量维度 | 标签数 |
---|---|---|---|---|
DBLP | 17 716 | 105 734 | 1 639 | 4 |
PubMed | 19 717 | 88 648 | 500 | 3 |
Citeseer | 4 230 | 5 358 | 602 | 6 |
ACM | 3 025 | 26 256 | 1 870 | 3 |
Coauthor | 34 493 | 495 924 | 8 415 | 5 |
图4 图节点特征在第0、50、100、150、200个周期优化后的t-SNE降维可视化结果
Fig. 4 Visualization results of t-SNE downscaling of graph node features after optimization at epoch of 0, 50, 100, 150,and 200
数据集 | Ms | |||||
---|---|---|---|---|---|---|
GraphSAGE | GAT | GIN | ||||
Acc | Fid | Acc | Fid | Acc | Fid | |
DBLP | 0.799±0.003 | 0.832±0.005 | 0.735±0.003 | 0.768±0.011 | 0.735±0.008 | 0.779±0.013 |
PubMed | 0.830±0.012 | 0.867±0.007 | 0.812±0.007 | 0.846±0.004 | 0.772±0.002 | 0.824±0.004 |
Citeseer | 0.812±0.002 | 0.853±0.005 | 0.809±0.004 | 0.847±0.003 | 0.758±0.015 | 0.797±0.010 |
ACM | 0.837±0.005 | 0.870±0.008 | 0.836±0.002 | 0.850±0.004 | 0.823±0.013 | 0.854±0.007 |
Coauthor | 0.866±0.001 | 0.889±0.005 | 0.856±0.005 | 0.882±0.003 | 0.846±0.004 | 0.877±0.010 |
表3 GraphSAGE作为目标模型架构时的攻击效果
Tab. 3 Attack performance with GraphSAGE as target model architecture
数据集 | Ms | |||||
---|---|---|---|---|---|---|
GraphSAGE | GAT | GIN | ||||
Acc | Fid | Acc | Fid | Acc | Fid | |
DBLP | 0.799±0.003 | 0.832±0.005 | 0.735±0.003 | 0.768±0.011 | 0.735±0.008 | 0.779±0.013 |
PubMed | 0.830±0.012 | 0.867±0.007 | 0.812±0.007 | 0.846±0.004 | 0.772±0.002 | 0.824±0.004 |
Citeseer | 0.812±0.002 | 0.853±0.005 | 0.809±0.004 | 0.847±0.003 | 0.758±0.015 | 0.797±0.010 |
ACM | 0.837±0.005 | 0.870±0.008 | 0.836±0.002 | 0.850±0.004 | 0.823±0.013 | 0.854±0.007 |
Coauthor | 0.866±0.001 | 0.889±0.005 | 0.856±0.005 | 0.882±0.003 | 0.846±0.004 | 0.877±0.010 |
数据集 | Ms | |||||
---|---|---|---|---|---|---|
GraphSAGE | GAT | GIN | ||||
Acc | Fid | Acc | Fid | Acc | Fid | |
DBLP | 0.758±0.002 | 0.811±0.006 | 0.812±0.001 | 0.846±0.004 | 0.749±0.004 | 0.788±0.013 |
PubMed | 0.781±0.005 | 0.832±0.004 | 0.832±0.002 | 0.874±0.001 | 0.768±0.002 | 0.820±0.002 |
Citeseer | 0.763±0.003 | 0.809±0.004 | 0.828±0.004 | 0.862±0.003 | 0.756±0.020 | 0.805±0.011 |
ACM | 0.823±0.004 | 0.857±0.002 | 0.845±0.002 | 0.879±0.006 | 0.813±0.001 | 0.847±0.003 |
Coauthor | 0.841±0.005 | 0.879±0.003 | 0.870±0.005 | 0.891±0.012 | 0.836±0.005 | 0.872±0.013 |
表4 GAT作为目标模型架构时的攻击效果
Tab. 4 Attack performance with GAT as target model architecture
数据集 | Ms | |||||
---|---|---|---|---|---|---|
GraphSAGE | GAT | GIN | ||||
Acc | Fid | Acc | Fid | Acc | Fid | |
DBLP | 0.758±0.002 | 0.811±0.006 | 0.812±0.001 | 0.846±0.004 | 0.749±0.004 | 0.788±0.013 |
PubMed | 0.781±0.005 | 0.832±0.004 | 0.832±0.002 | 0.874±0.001 | 0.768±0.002 | 0.820±0.002 |
Citeseer | 0.763±0.003 | 0.809±0.004 | 0.828±0.004 | 0.862±0.003 | 0.756±0.020 | 0.805±0.011 |
ACM | 0.823±0.004 | 0.857±0.002 | 0.845±0.002 | 0.879±0.006 | 0.813±0.001 | 0.847±0.003 |
Coauthor | 0.841±0.005 | 0.879±0.003 | 0.870±0.005 | 0.891±0.012 | 0.836±0.005 | 0.872±0.013 |
数据集 | Ms | |||||
---|---|---|---|---|---|---|
GraphSAGE | GAT | GIN | ||||
Acc | Fid | Acc | Fid | Acc | Fid | |
DBLP | 0.742±0.002 | 0.773±0.003 | 0.733±0.002 | 0.769±0.010 | 0.806±0.005 | 0.822±0.003 |
PubMed | 0.774±0.006 | 0.791±0.004 | 0.758±0.003 | 0.801±0.003 | 0.819±0.004 | 0.835±0.002 |
Citeseer | 0.760±0.017 | 0.782±0.005 | 0.741±0.002 | 0.796±0.001 | 0.811±0.002 | 0.847±0.003 |
ACM | 0.790±0.003 | 0.828±0.003 | 0.808±0.004 | 0.832±0.003 | 0.841±0.005 | 0.863±0.002 |
Coauthor | 0.832±0.005 | 0.856±0.010 | 0.838±0.005 | 0.861±0.004 | 0.859±0.002 | 0.877±0.004 |
表5 GIN作为目标模型架构时的攻击效果
Tab. 5 Attack performance with GIN as target model architecture
数据集 | Ms | |||||
---|---|---|---|---|---|---|
GraphSAGE | GAT | GIN | ||||
Acc | Fid | Acc | Fid | Acc | Fid | |
DBLP | 0.742±0.002 | 0.773±0.003 | 0.733±0.002 | 0.769±0.010 | 0.806±0.005 | 0.822±0.003 |
PubMed | 0.774±0.006 | 0.791±0.004 | 0.758±0.003 | 0.801±0.003 | 0.819±0.004 | 0.835±0.002 |
Citeseer | 0.760±0.017 | 0.782±0.005 | 0.741±0.002 | 0.796±0.001 | 0.811±0.002 | 0.847±0.003 |
ACM | 0.790±0.003 | 0.828±0.003 | 0.808±0.004 | 0.832±0.003 | 0.841±0.005 | 0.863±0.002 |
Coauthor | 0.832±0.005 | 0.856±0.010 | 0.838±0.005 | 0.861±0.004 | 0.859±0.002 | 0.877±0.004 |
1 | 任奎, 孟泉润, 闫守琨, 等. 人工智能模型数据泄露的攻击与防御研究综述[J].网络与信息安全学报, 2021, 7(1): 1-10. |
REN K, MENG Q R, YAN S K, et al. Survey of artificial intelligence data security and privacy protection[J]. Chinese Journal of Network and Information Security, 2021, 7(1): 1-10. | |
2 | 李欣姣,吴国伟,姚琳,等. 机器学习安全攻击与防御机制研究进展和未来挑战[J]. 软件学报, 2021, 32(2): 406-423. |
LI X J, WU G W, YAO L, et al. Progress and future challenges of security attacks and defense mechanisms in machine learning[J]. Journal of Software, 2021, 32(2): 406-423. | |
3 | GONG X, WANG Q, CHEN Y, et al. Model extraction attacks and defenses on cloud-based machine learning models[J]. IEEE Communications Magazine, 2020, 58(12): 83-89. |
4 | OREKONDY T, SCHIELE B, FRITZ M. Knockoff nets: stealing functionality of black-box models[C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 4949-4958. |
5 | PAPERNOT N, McDANIEL P, GOODFELLOW I, et al. Practical black-box attacks against machine learning[C]// Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security. New York: ACM, 2017: 506-519. |
6 | 陈传涛, 潘丽敏, 罗森林, 等. 基于FGSM样本扩充的模型窃取攻击方法研究[J]. 信息安全研究, 2021, 7(11): 1023-1030. |
CHEN C T, PAN L M, LUO S L, et al. Research on model stealing attack method based on FGSM sample expansion[J]. Journal of Information Security Research, 2021, 7(11): 1023-1030. | |
7 | KARIYAPPA S, PRAKASH A, QURESHI M K. MAZE: data-free model stealing attack using zeroth-order gradient estimation[C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 13809-13818. |
8 | YUAN X, DING L, ZHANG L, et al. ES attack: model stealing against deep neural networks without data hurdles[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2022, 6(5): 1258-1270. |
9 | J-B TRUONG, MAINI P, WALLS R J, et al. Data-free model extraction[C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE,2021: 4767-4778. |
10 | MIURA T, HASEGAWA S, SHIBAHARA T. MEGEX: data-free model extraction attack against gradient-based explainable AI[EB/OL].(2021-07-19) [2023-08-17].. |
11 | HONG C, HUANG J, CHEN L Y. MEGA: model stealing via collaborative generator-substitute networks[EB/OL].(2022-01-31)[2023-08-17].. |
12 | SANYAL S, ADDEPALLI S, BABU R V.Towards data-free model stealing in a hard label setting[C]// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 15263-15272. |
13 | TASUMI M, IWAHANA K, YANAI N, et al. First to possess his statistics: data-free model extraction attack on tabular data[EB/OL].(2021-09-30)[2023-08-17].. |
14 | DeFAZIO D, RAMESH A. Adversarial model extraction on graph neural networks[EB/OL].(2019-12-16)[2023-08-17]. . |
15 | WU B, YANG X, PAN S, et al. Model extraction attacks on graph neural networks: taxonomy and realisation[C]// Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security. New York: ACM, 2022: 337-350. |
16 | SHEN Y, HE X, HAN Y, et al. Model stealing attacks against inductive graph neural networks[C]// Proceedings of the 2022 IEEE Symposium on Security and Privacy. Piscataway: IEEE,2022: 1175-1192. |
17 | FRANCESCHI L, NIEPERT M, PONTIL M, et al. Learning discrete structures for graph neural networks[J]. Proceedings of Machine Learning Research, 2019, 97: 1972-1982. |
18 | CHEN Y, WU L, ZAKI M J. Iterative deep graph learning for graph neural networks: better and robust node embeddings [J].Advances in Neural Information Processing Systems, 2020, 33: 19314-19326. |
19 | YUAN H, YU H, GUI S, et al. Explainability in graph neural networks: a taxonomic survey[EB/OL].(2022-07-01)[2023-08-17]. . |
20 | YING R, BOURGEOIS D, YOU J, et al. GNNExplainer: generating explanations for graph neural networks[J].Advances in Neural Information Processing Systems, 2019, 32: 9244-9255. |
21 | RONG Y, HUANG W, XU T, et al.DropEdge: towards deep graph convolutional networks on node classification[EB/OL].(2020-03-12)[2023-08-17].. |
22 | CHEN D, LIN Y, LI W, et al. Measuring and relieving the over-smoothing problem for graph neural networks from the topological view[EB/OL].(2019-11-18)[2023-08-17]. . |
23 | ZHANG Y, PAL S, COATES M, et al.Bayesian graph convolutional neural networks for semi-supervised classification[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 5829-5836. |
24 | ZHAO T, LIU Y, NEVES L, et al.Data augmentation for graph neural networks[EB/OL].(2020-12-02)[2023-08-17]. . |
25 | KIPF TN, WELLING M.Variational graph auto-encoders[EB/OL].(2016-11-21)[2023-08-17]. . |
26 | XU J, CHEN J, YOU S, et al. Robustness of deep learning models on graphs: a survey[J]. AI Open, 2021, 2: 69-78. |
[1] | 杜郁, 朱焱. 构建预训练动态图神经网络预测学术合作行为消失[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2726-2731. |
[2] | 杨兴耀, 陈羽, 于炯, 张祖莲, 陈嘉颖, 王东晓. 结合自我特征和对比学习的推荐模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2704-2710. |
[3] | 杨航, 李汪根, 张根生, 王志格, 开新. 基于图神经网络的多层信息交互融合算法用于会话推荐[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2719-2725. |
[4] | 唐廷杰, 黄佳进, 秦进. 基于图辅助学习的会话推荐[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2711-2718. |
[5] | 杨帆, 邹窈, 朱明志, 马振伟, 程大伟, 蒋昌俊. 基于图注意力Transformer神经网络的信用卡欺诈检测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2634-2642. |
[6] | 林欣蕊, 王晓菲, 朱焱. 基于局部扩展社区发现的学术异常引用群体检测[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1855-1861. |
[7] | 汪炅, 唐韬韬, 贾彩燕. 无负采样的正样本增强图对比学习推荐方法PAGCL[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1485-1492. |
[8] | 郭洁, 林佳瑜, 梁祖红, 罗孝波, 孙海涛. 基于知识感知和跨层次对比学习的推荐方法[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1121-1127. |
[9] | 徐大鹏, 侯新民. 基于网络结构设计的图神经网络特征选择方法[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 663-670. |
[10] | 胡能兵, 蔡彪, 李旭, 曹旦华. 基于图池化对比学习的图分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3327-3334. |
[11] | 花晓雨, 李冬芬, 付优, 毕可骏, 应时, 王瑞锦. 结合层次图神经网络与长短期记忆的产业链风险评估预警模型[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3223-3231. |
[12] | 周北京, 王海荣, 王怡梦, 张丽丝, 马赫. 图谱嵌入传播的推荐方法[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3252-3259. |
[13] | 王红斌, 房晓, 江虹. 融入三维语义特征的常识推理问答方法[J]. 《计算机应用》唯一官方网站, 2024, 44(1): 138-144. |
[14] | 罗俊豪, 朱焱. 用于未对齐多模态语言序列情感分析的多交互感知网络[J]. 《计算机应用》唯一官方网站, 2024, 44(1): 79-85. |
[15] | 马国帅, 钱宇华, 张亚宇, 李俊霞, 刘郭庆. 动态异构信息融合的科研合作潜力预测[J]. 《计算机应用》唯一官方网站, 2023, 43(9): 2775-2783. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||