{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:39:48Z","timestamp":1759365588523,"version":"build-2065373602"},"reference-count":35,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Computers"],"abstract":"<jats:p>Graph neural networks (GNNs) are deep learning models that process structured graph data. By leveraging their graphs\/node classification and link prediction capabilities, they have been effectively applied in multiple domains such as community detection, location sharing services, and drug discovery. These powerful applications and the vast availability of graphs in diverse fields have facilitated the adoption of GNNs in privacy-sensitive contexts (e.g., banking systems and healthcare). Unfortunately, GNNs are vulnerable to the leakage of sensitive information through well-defined attacks. Our main focus is on membership inference attacks (MIAs) that allow the attacker to infer whether a given sample belongs to the training dataset. To prevent this, we introduce three LLM-guided defense mechanisms applied at the posterior level: posterior encoding with noise, knowledge distillation, and secure aggregation. Our proposed approaches not only successfully reduce MIA accuracy but also maintain the model\u2019s performance on the node classification task. Our findings, validated through extensive experiments on widely used GNN architectures, offer insights into balancing privacy preservation with predictive performance.<\/jats:p>","DOI":"10.3390\/computers14100414","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T07:58:13Z","timestamp":1759305493000},"page":"414","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Do LLMs Offer a Robust Defense Mechanism Against Membership Inference Attacks on Graph Neural Networks?"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7506-8582","authenticated-orcid":false,"given":"Abdellah","family":"Jnaini","sequence":"first","affiliation":[{"name":"Department of Computer Science, National School of Applied Sciences, Mohammed First University, Oujda 60000, Morocco"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3284-1237","authenticated-orcid":false,"given":"Mohammed-Amine","family":"Koulali","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National School of Applied Sciences, Mohammed First University, Oujda 60000, Morocco"},{"name":"College of Computing, Mohammed VI Polytechnic University (UM6P), Ben Guerir 43150, Morocco"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., and Manning, C.D. (2015, January 17\u201321). Effective approaches to attention-based neural machine translation. Proceedings of the Empirical Methods in Natural Language Processing (EMNLP), Lisbon, Portugal.","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref_2","unstructured":"Wu, Y., Schuster, M., Chen, Z., Le, Q.V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., and Macherey, K. (2016). Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups","volume":"29","author":"Hinton","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_5","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7\u201312). Faster r-cnn: Towards real-time object detection with region proposal networks. Proceedings of the 28th Annual Conference on Neural Information Processing Systems (NIPS), Montreal, QC, Canada."},{"key":"ref_6","first-page":"1995","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"LeCun","year":"1995","journal-title":"Handb. Brain Theory Neural Netw."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_8","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/MSP.2017.2693418","article-title":"Geometric deep learning: Going beyond Euclidean data","volume":"34","author":"Bronstein","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_10","unstructured":"Hamilton, W.L., Ying, R., and Leskovec, J. (2017, January 4\u20139). Representation learning on graphs: Methods and applications. Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS), Long Beach, CA, USA."},{"key":"ref_11","unstructured":"Battaglia, P.W., Hamrick, J.B., Bapst, V., Sanchez-Gonzalez, A., Zambaldi, V., Malinowski, M., Tacchetti, A., Raposo, D., Santoro, A., and Faulkner, R. (2018). Relational inductive biases, deep learning, and graph networks. arXiv."},{"key":"ref_12","unstructured":"Luan, S., Hua, C., Lu, Q., Zhu, J., Chang, X.W., and Precup, D. (2022). When Do We Need GNN for Node Classification?. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhou, F., Cao, C., Zhang, K., Trajcevski, G., Zhong, T., and Geng, J. (2019, January 3\u20137). Meta-gnn: On few-shot node classification in graph meta-learning. Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, China.","DOI":"10.1145\/3357384.3358106"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"56083","DOI":"10.1109\/ACCESS.2023.3283029","article-title":"LeL-GNN: Learnable Edge Sampling and Line based Graph Neural Network for Link Prediction","volume":"11","author":"Morshed","year":"2023","journal-title":"IEEE Access"},{"key":"ref_15","unstructured":"Errica, F., Podda, M., Bacciu, D., and Micheli, A. (2019). A fair comparison of graph neural networks for graph classification. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1605","DOI":"10.1109\/TNSE.2023.3326359","article-title":"An Empirical Evaluation of the Data Leakage in Federated Graph Learning","volume":"11","author":"Chen","year":"2023","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Carlini, N., Chien, S., Nasr, M., Song, S., Terzis, A., and Tramer, F. (2022, January 22\u201326). Membership inference attacks from first principles. Proceedings of the 2022 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA.","DOI":"10.1109\/SP46214.2022.9833649"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Jayaraman, B., and Evans, D. (2022, January 7\u201311). Are attribute inference attacks just imputation?. Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, Los Angeles, CA, USA.","DOI":"10.1145\/3548606.3560663"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wang, X., and Wang, W.H. (2022, January 7\u201311). Group property inference attacks against graph neural networks. Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, Los Angeles, CA, USA.","DOI":"10.1145\/3548606.3560662"},{"key":"ref_20","unstructured":"Wang, Y., Huang, L., Yu, P.S., and Sun, L. (2021). Membership Inference Attacks on Knowledge Graphs. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Olatunji, I.E., Nejdl, W., and Khosla, M. (2021, January 13\u201315). Membership inference attack on graph neural networks. Proceedings of the 2021 Third IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA), Atlanta, GA, USA.","DOI":"10.1109\/TPSISA52974.2021.00002"},{"key":"ref_22","unstructured":"He, X., Wen, R., Wu, Y., Backes, M., Shen, Y., and Zhang, Y. (2021). Node-level membership inference attacks against graph neural networks. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, X., Chen, C., Lin, S., and Li, J. (2022, January 16\u201318). Membership Inference Attacks Against Robust Graph Neural Network. Proceedings of the International Symposium on Cyberspace Safety and Security, Xi\u2019an, China.","DOI":"10.1007\/978-3-031-18067-5_19"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wang, X., and Wang, W.H. (2023, January 4\u20138). Link Membership Inference Attacks against Unsupervised Graph Representation Learning. Proceedings of the 39th Annual Computer Security Applications Conference, Austin, TX, USA.","DOI":"10.1145\/3627106.3627115"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"149","DOI":"10.56553\/popets-2023-0103","article-title":"Disparate Vulnerability in Link Inference Attacks against Graph Neural Networks","volume":"4","author":"Zhong","year":"2023","journal-title":"Proc. Priv. Enhancing Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.1007\/s10994-018-5724-2","article-title":"Similarity encoding for learning with dirty categorical variables","volume":"107","author":"Cerda","year":"2018","journal-title":"Mach. Learn."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wang, Z., Huang, N., Sun, F., Ren, P., Chen, Z., Luo, H., de Rijke, M., and Ren, Z. (2022, January 14\u201318). Debiasing learning for membership inference attacks against recommender systems. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington DC, USA.","DOI":"10.1145\/3534678.3539392"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Jnaini, A., Bettar, A., and Koulali, M.A. (2022, January 6\u20138). How Powerful are Membership Inference Attacks on Graph Neural Networks?. Proceedings of the 34th International Conference on Scientific and Statistical Database Management, Copenhagen, Denmark.","DOI":"10.1145\/3538712.3538737"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Nasr, M., Shokri, R., and Houmansadr, A. (2018, January 15\u201319). Machine learning with membership privacy using adversarial regularization. Proceedings of the 2018 ACM SIGSAC conference on computer and communications security, Toronto, ON, Canada.","DOI":"10.1145\/3243734.3243855"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1007\/s10207-022-00646-y","article-title":"Defense against membership inference attack in graph neural networks through graph perturbation","volume":"22","author":"Wang","year":"2023","journal-title":"Int. J. Inf. Secur."},{"key":"ref_31","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1109\/JPROC.2024.3369017","article-title":"Trustworthy graph neural networks: Aspects, methods, and trends","volume":"112","author":"Zhang","year":"2024","journal-title":"Proc. IEEE"},{"key":"ref_33","unstructured":"Singh, A., Thakur, N., and Sharma, A. (2016, January 16\u201318). A review of supervised machine learning algorithms. Proceedings of the 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/s40708-017-0065-7","article-title":"Machine learning\u2013XGBoost analysis of language networks to classify patients with epilepsy","volume":"4","author":"Torlay","year":"2017","journal-title":"Brain Inform."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.isprsjprs.2016.01.011","article-title":"Random forest in remote sensing: A review of applications and future directions","volume":"114","author":"Belgiu","year":"2016","journal-title":"ISPRS J. Photogramm. Remote Sens."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/10\/414\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T08:08:54Z","timestamp":1759306134000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/10\/414"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"references-count":35,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["computers14100414"],"URL":"https:\/\/doi.org\/10.3390\/computers14100414","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,1]]}}}