Comprehensive study of Integrating Clustering and Adversarial Learning for Enhanced Recommender Systems: A Systematic Review of Hybrid Methodologies and Applications
Article Sidebar
Main Article Content
Abstract
Recommender systems (RSs) have become critical elements in modern instances of information and decision-support systems, resulting in a transformation of user experiences through highly personalized suggestions for an undeniably vast range of items. Although RSs have become commonplace, they continue to evolve, and their challenges, including sparsity, cold-start, scalability, and vulnerability to adversarial challenges remain. The use of clustering methods has proven highly effective in resolving these issues through the discovery and exploitation of latent user behaviour patterns, segmenting user groups that contribute more towards personalized and adaptable RSs. Additionally, adversarial learning has become a growing focus of study as a proposed solution for shielding and defending RSs, processes, and data from manipulation and attacks, resulting in greater resistance and trustworthiness. This study presents a systematic literature review (SLR) that explores the intersection of RSs, clustering methods, and adversarial learning. This paper synthesizes a critique of the latest hybrid recommendations, detailing motivations, challenges, directions for future study, and practical recommendations drawn from the examined studies. An SLR search of four academic databases, ScienceDirect (SD), IEEE Xplore (IEEE), Scopus, and Web of Science (WoS), delivered an initial yield of 843 studies; after filtration, 51 studies remained. All the retained articles were examined and characterized in terms of dataset details, techniques, frameworks, and performance. A significant gap in research has emerged regarding the overreliance on datasets from commercial and entertainment domains, with a notable scarcity of studies addressing critical domains such as healthcare, finance, and other critical fields where diverse data sources should invoke robust, secure, and trustworthy RSs recommendations. Future research is needed to develop adversarially robust RSs for high-stakes applications requiring stringent accuracy and safety standards. This review provides a rich critical examination of the literature to embolden the ideas and theories associated with clustering methods and adversarial learning working together within RSs. It offers concrete opportunities and directions for carrying out future work in developing next-generation secure, adaptive recommendation frameworks. These findings corroborate a change in perspective on designing systems that seek to develop an RSs that can withstand adversarial threats and promote the development of safer, fairer, and more reliable decision-support systems in a variety of domains.
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
[1] B. Dong, Y. Zhu, L. Li, and X. Wu, “Hybrid Collaborative Recommendation via Dual-Autoencoder,” IEEE Access, vol. 8, pp. 46030–46040, 2020, doi: 10.1109/ACCESS.2020.2979255.
[2] Q. Zhou and C. Huang, “A recommendation attack detection approach integrating CNN with Bagging,” Comput. Secur., vol. 146, 2024, doi: 10.1016/j.cose.2024.104030.
[3] Y. Hao, H. Wang, Q. Zhao, L. Feng, and J. Wang, “Detecting the adversarially-learned injection attacks via knowledge graphs,” Inf. Syst., vol. 125, p. 102419, 2024, doi: 10.1016/j.is.2024.102419.
[4] L. Li, Z. Zhang, and S. Zhang, “Hybrid Algorithm Based on Content and Collaborative Filtering in Recommendation System Optimization and Simulation,” Sci. Program., vol. 2021, 2021, doi: 10.1155/2021/7427409.
[5] F. Zhou, Y. Mo, G. Trajcevski, K. Zhang, J. Wu, and T. Zhong, “Recommendation via Collaborative Autoregressive Flows,” Neural Networks, vol. 126, pp. 52–64, 2020, doi: 10.1016/j.neunet.2020.03.010.
[6] M. H. Hadid et al., “Semantic Image Retrieval Analysis Based on Deep Learning and Singular Value Decomposition,” Appl. Data Sci. Anal., vol. 2024, pp. 17–31, 2024, doi: 10.58496/adsa/2024/003.
[7] M. A. Ahmed et al., “Intelligent Decision-Making Framework for Evaluating and Benchmarking Hybridized Multi-Deep Transfer Learning Models: Managing COVID-19 and Beyond,” Int. J. Inf. Technol. Decis. Mak., Apr. 2023, doi: 10.1142/S0219622023500463.
[8] S. S. Joudar, R. A. Hamid, I. A. Zahid, G. Kou, and I. M. Sharaf, “Explainable artificial intelligence multimodal of autism triage levels using fuzzy approach-based multi-criteria decision-making and LIME,” Int. J. Fuzzy Syst., vol. 26, no. 1, pp. 274–303, 2024.
[9] A. S. Albahri et al., “A Trustworthy and Explainable Framework for Benchmarking Hybrid Deep Learning Models Based on Chest X-Ray Analysis in CAD Systems,” Int. J. Inf. Technol. Decis. Mak., pp. 1–54, Jan. 2024, doi: 10.1142/S0219622024500019.
[10] L. A. E. Al-Saeedi et al., “Artificial Intelligence and Cybersecurity in Face Sale Contracts: Legal Issues and Frameworks,” 2024. doi: 10.58496/MJCS/2024/0012.
[11] T. Al-Quraishi, C. Keong NG, O. A. Mahdi, A. Gyasi, and N. Al-Quraishi, “Advanced Ensemble Classifier Techniques for Predicting Tumor Viability in Osteosarcoma Histological Slide Images,” Appl. Data Sci. Anal., vol. 2024, pp. 52–68, 2024, doi: 10.58496/adsa/2024/006.
[12] R. Nai, R. Meo, G. Morina, and P. Pasteris, “Public tenders, complaints, machine learning and recommender systems: a case study in public administration,” Comput. Law Secur. Rev., vol. 51, p. 105887, 2023, doi: https://doi.org/10.1016/j.clsr.2023.105887.
[13] F. K. H. Mihna et al., “Bridging Law and Machine Learning: A Cybersecure Model for Classifying Digital Real Estate Contracts in the Metaverse,” 2025. doi: 10.58496/MJBD/2025/003.
[14] M. E. Alqaysi, A. S. Albahri, and R. A. Hamid, “Evaluation and benchmarking of hybrid machine learning models for autism spectrum disorder diagnosis using a 2-tuple linguistic neutrosophic fuzzy sets-based decision-making model,” Neural Comput. Appl., vol. 36, no. 29, pp. 18161–18200, 2024.
[15] M. E. Alqaysi, A. S. Albahri, and R. A. Hamid, “Hybrid Diagnosis Models for Autism Patients Based on Medical and Sociodemographic Features Using Machine Learning and Multicriteria Decision-Making ( MCDM ) Techniques : An Evaluation and Benchmarking Framework,” vol. 2022, no. ii, 2022.
[16] A. A. A. Lateef, A. S. Abdalkafor, and A. A. Nafea, “Optimized KNN Algorithm for Diabetic Retinopathy Classification with PCA-Based Data Fusion and Cuckoo Search Optimization,” J. Intell. Syst. Internet Things, vol. 15, no. 1, pp. 122–132, 2025, doi: 10.54216/JISIoT.150110.
[17] A. S. Abdalkafor and K. M. A. Alheeti, “K-Nearest Neighbor Algorithm for Efficient Heart Disease Classification System,” in 2023 15th International Conference on Developments in eSystems Engineering (DeSE), 2023, pp. 527–532. doi: 10.1109/DeSE58274.2023.10099808.
[18] F. H. Awad and M. M. Hamad, “Improved k-Means Clustering Algorithm for Big Data Based on Distributed SmartphoneNeural Engine Processor,” 2022. doi: 10.3390/electronics11060883.
[19] A. Ahmed, K. Saleem, O. Khalid, J. Gao, and U. Rashid, “Trust-aware denoising autoencoder with spatial-temporal activity for cross-domain personalized recommendations,” Neurocomputing, vol. 511, pp. 477–494, 2022, doi: 10.1016/j.neucom.2022.09.023.
[20] F. H. Awad, M. M. Hamad, and L. Alzubaidi, “Robust Classification and Detection of Big Medical Data Using Advanced Parallel K-Means Clustering, YOLOv4, and Logistic Regression,” 2023. doi: 10.3390/life13030691.
[21] H. Wen, W. Guo, and X. Li, “A novel deep clustering network using multi-representation autoencoder and adversarial learning for large cross-domain fault diagnosis of rolling bearings,” Expert Syst. Appl., vol. 225, 2023, doi: 10.1016/j.eswa.2023.120066.
[22] J. Wang, M. Gao, Z. Wang, C. Lin, W. Zhou, and J. Wen, “Ada: Adversarial learning based data augmentation for malicious users detection,” Appl. Soft Comput., vol. 117, p. 108414, 2022, doi: 10.1016/j.asoc.2022.108414.
[23] Y. Lai, Y. Zhu, W. Fan, X. Zhang, and K. Zhou, “Toward adversarially robust recommendation from adaptive fraudster detection,” IEEE Trans. Inf. Forensics Secur., vol. 19, pp. 907–919, 2023.
[24] A. S. Albahri et al., “Trust and explainability in robotic hand control via adversarial multiple machine learning models with EEG sensor data fusion: A fuzzy decision-making solution,” Comput. Biol. Med., vol. 196, p. 110922, 2025, doi: 10.1016/j.compbiomed.2025.110922.
[25] W. Fan et al., “Adversarial Attacks for Black-Box Recommender Systems via Copying Transferable Cross-Domain User Profiles,” IEEE Trans. Knowl. Data Eng., vol. 35, no. 12, pp. 12415–12429, 2023, doi: 10.1109/TKDE.2023.3272652.
[26] F. Hazzaa, M. M. Hasan, A. Qashou, and S. Yousef, “A new lightweight cryptosystem for IoT in smart city environments,” Mesopotamian J. CyberSecurity, vol. 4, no. 3, pp. 46–58, 2024.
[27] Z. Shen, X. Guo, B. Feng, H. Cheng, S. Ni, and H. Dong, “Adversarial learning based residual variational graph normalized autoencoder for network representation,” Inf. Sci. (Ny)., vol. 640, Sep. 2023, doi: 10.1016/j.ins.2023.119055.
[28] A. E. Cinà, A. Torcinovich, and M. Pelillo, “A black-Box adversarial attack for poisoning clustering,” Pattern Recognit., vol. 122, 2022, doi: 10.1016/j.patcog.2021.108306.
[29] L. Yang, S. X. Yang, Y. Li, Y. Lu, and T. Guo, “Generative Adversarial Learning for Trusted and Secure Clustering in Industrial Wireless Sensor Networks,” 2023. doi: 10.1109/TIE.2022.3212378.
[30] F. A. Al-Ibraheemi et al., “Intrusion Detection in Software-Defined Networks: Leveraging Deep Reinforcement Learning with Graph Convolutional Networks for Resilient Infrastructure.,” Fusion Pract. Appl., vol. 15, no. 1, 2024.
[31] Y. Wang, Y. Liu, Q. Wang, and C. Wang, “ClusterPoison: Poisoning Attacks on Recommender Systems with Limited Fake Users,” IEEE Commun. Mag., vol. 62, no. 11, pp. 136–142, 2024, doi: 10.1109/MCOM.001.2300558.
[32] L. Li, J. Xiahou, F. Lin, and S. Su, “DistVAE: Distributed Variational Autoencoder for sequential recommendation,” Knowledge-Based Syst., vol. 264, p. 110313, 2023, doi: 10.1016/j.knosys.2023.110313.
[33] D. Moher, A. Liberati, J. Tetzlaff, D. G. Altman, and P. Group, “Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement,” Int. J. Surg., vol. 8, no. 5, pp. 336–341, 2010.
[34] M. E. Alqaysi, A. S. Albahri, and R. A. Hamid, “Diagnosis‐based hybridization of multimedical tests and sociodemographic characteristics of autism spectrum disorder using artificial intelligence and machine learning techniques: a systematic review,” Int. J. Telemed. Appl., vol. 2022, no. 1, p. 3551528, 2022.
[35] S. S. Joudar, R. A. Hamid, and I. A. Zahid, “Artificial intelligence-based approaches for improving the diagnosis, triage, and prioritization of autism spectrum disorder: a systematic review of current trends and open issues,” Artif. Intell. Rev., vol. 56, no. Suppl 1, pp. 53–117, 2023.
[36] H. A. Al-Tameemi et al., “A Systematic Review of Metaverse Cybersecurity: Frameworks, Challenges, and Strategic Approaches in a Quantum-Driven Era,” Mesopotamian J. CyberSecurity, vol. 5, no. 2, pp. 770–803, 2025, doi: 10.58496/MJCS/2025/045.
[37] J. Yu, L. Zhao, S. Yin, and M. Ivanovic, “News Recommendation Model Based on Encoder Graph Neural Network and Bat Optimization in Online Social Multimedia Art Education,” Comput. Sci. Inf. Syst., vol. 21, no. 3, pp. 989–1012, 2024, doi: 10.2298/CSIS231225025Y.
[38] J. Chen et al., “N2VSCDNNR: A Local Recommender System Based on Node2vec and Rich Information Network,” 2019. doi: 10.1109/TCSS.2019.2906181.
[39] R. Kashef, “Enhancing the role of large-scale recommendation systems in the IoT context,” IEEE Access, vol. 8, pp. 178248–178257, 2020, doi: 10.1109/ACCESS.2020.3026310.
[40] M. Bazargani, S. H.Alizadeh, and B. Masoumi, “Group deep neural network approach in semantic recommendation system for movie recommendation in networks online,” Electron. Commer. Res., 2024, doi: 10.1007/s10660-024-09897-4.
[41] J. Chinnadurai et al., “Enhancing online education recommendations through clustering-driven deep learning,” Biomed. Signal Process. Control, vol. 97, 2024, doi: 10.1016/j.bspc.2024.106669.
[42] Y. Niu, Y. Su, S. Li, S. Wan, and X. Cao, “Deep adversarial autoencoder recommendation algorithm based on group influence,” Inf. Fusion, vol. 100, p. 101903, 2023, doi: 10.1016/j.inffus.2023.101903.
[43] N. Khouibiri, Y. Farhaoui, and A. El Allaoui, “Design and Analysis of a Recommendation System Based on Collaborative Filtering Techniques for Big Data,” Intell. Converg. Networks, vol. 4, no. 4, pp. 296–304, 2023, doi: 10.23919/ICN.2023.0024.
[44] Y. Zhang and X. Gu, “Enhancing user and item representation with collaborative signals for KG-based recommendation,” Neural Comput. Appl., vol. 36, no. 12, pp. 6681–6699, 2024, doi: 10.1007/s00521-024-09419-1.
[45] A. Chhabra, A. Roy, and P. Mohapatra, “Suspicion-free adversarial attacks on clustering algorithms,” 2020, Univ Calif Davis, tDept Comp Sci, Davis, CA 95616 USA. doi: 10.1609/aaai.v34i04.5770.
[46] C. Zhang and Z. Tang, “Novel poisoning attacks for clustering methods via robust feature generation,” Neurocomputing, vol. 598, 2024, doi: 10.1016/j.neucom.2024.127925.
[47] H. Xia, S. Shao, C. Hu, R. Zhang, T. Qiu, and F. Xiao, “Robust Clustering Model Based on Attention Mechanism and Graph Convolutional Network,” IEEE Trans. Knowl. Data Eng., vol. 35, no. 5, pp. 5203–5215, 2023, doi: 10.1109/TKDE.2022.3150300.
[48] W. Yang, M. Wang, C. Tang, X. Zheng, X. Liu, and K. He, “Trustworthy multi-view clustering via alternating generative adversarial representation learning and fusion,” Inf. Fusion, vol. 107, 2024, doi: 10.1016/j.inffus.2024.102323.
[49] Q. Lv, N. Yang, A. Slowik, J. Lv, and A. Yousefpour, “Market behavior-oriented deep learning-based secure data analysis in smart cities,” Comput. Electr. Eng., vol. 108, 2023, doi: 10.1016/j.compeleceng.2023.108722.
[50] X. Ye, J. Zhao, Y. Chen, and L. J. Guo, “Bayesian Adversarial Spectral Clustering with Unknown Cluster Number,” IEEE Trans. Image Process., vol. 29, pp. 8506–8518, 2020, doi: 10.1109/TIP.2020.3016491.
[51] C. Pimsarn, T. Boongoen, N. Iam-On, N. Naik, and L. Yang, “Strengthening intrusion detection system for adversarial attacks: improved handling of imbalance classification problem,” 2022. doi: 10.1007/s40747-022-00739-0.
[52] H. Shirazi, B. Bezawada, I. Ray, and C. Anderson, “Directed adversarial sampling attacks on phishing detection,” J. Comput. Secur., vol. 29, no. 1, pp. 1–23, 2021, doi: 10.3233/JCS-191411.
[53] P. Tatongjai, T. Boongoen, N. Iam-On, N. Naik, and L. Yang, “Classification of Adversarial Attacks Using Ensemble Clustering Approach,” Comput. Mater. Contin., vol. 74, no. 2, pp. 2479–2498, 2023, doi: 10.32604/cmc.2023.024858.
[54] W. Tang, B. Hui, L. Tian, G. Luo, Z. He, and Z. Cai, “Learning disentangled user representation with multi-view information fusion on social networks,” Inf. Fusion, vol. 74, pp. 77–86, 2021, doi: 10.1016/j.inffus.2021.03.011.
[55] G. Delorme, Y. Xu, S. Lathuilière, R. Horaud, and X. Alameda-Pineda, “CANU-ReID: a conditional adversarial network for unsupervised person re-identification,” in 2020 25th International Conference on Pattern Recognition (ICPR), IEEE, 2021, pp. 4428–4435.
[56] C. Sandoval, E. Pirogova, and M. Lech, “Adversarial learning approach to unsupervised labeling of fine art paintings,” 2021. doi: 10.1109/ACCESS.2021.3086476.
[57] S. Rass, S. Konig, S. Ahmad, and M. Goman, “Metricizing the Euclidean Space Toward Desired Distance Relations in Point Clouds,” IEEE Trans. Inf. Forensics Secur., vol. 19, pp. 7304–7319, 2024, doi: 10.1109/TIFS.2024.3420246.
[58] D. He et al., “Adversarial representation mechanism learning for network embedding,” IEEE Trans. Knowl. Data Eng., vol. 35, no. 2, pp. 1200–1213, 2021.
[59] H. Ma et al., “Stealthy attack on graph recommendation system,” Expert Syst. Appl., vol. 255, p. 124476, 2024, doi: 10.1016/j.eswa.2024.124476.
[60] Q. Wang, C. Wu, D. Lian, and E. Chen, “Securing recommender system via cooperative training,” World Wide Web, vol. 26, no. 6, pp. 3915–3943, 2023, doi: 10.1007/s11280-023-01214-7.
[61] T. Baker, T. Li, J. Jia, B. Zhang, C. Tan, and A. Y. Zomaya, “Poison-Tolerant Collaborative Filtering Against Poisoning Attacks on Recommender Systems,” IEEE Trans. Dependable Secur. Comput., vol. 21, no. 5, pp. 4589–4599, 2024, doi: 10.1109/TDSC.2024.3354462.
[62] C. Wu, D. Lian, Y. Ge, Z. Zhu, and E. Chen, “Influence-Driven Data Poisoning for Robust Recommender Systems,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 10, pp. 11915–11931, 2023, doi: 10.1109/TPAMI.2023.3274759.
[63] Q. Zhou, K. Li, and L. Duan, “Recommendation attack detection based on improved Meta Pseudo Labels,” Knowledge-Based Syst., vol. 279, 2023, doi: 10.1016/j.knosys.2023.110931.
[64] H. Cai, J. Ren, J. Zhao, S. Yuan, and J. Meng, “KC-GCN: A Semi-Supervised Detection Model against Various Group Shilling Attacks in Recommender Systems,” Wirel. Commun. Mob. Comput., vol. 2023, 2023, doi: 10.1155/2023/2854874.
[65] Y. Du, M. Fang, J. Yi, C. Xu, J. Cheng, and D. Tao, “Enhancing the robustness of neural collaborative filtering systems under malicious attacks,” IEEE Trans. Multimed., vol. 21, no. 3, pp. 555–565, 2018.
[66] H. Liu, L. Guo, P. Li, P. Zhao, and X. Wu, Collaborative filtering with a deep adversarial and attention network for cross-domain recommendation, vol. 565. 2021. doi: 10.1016/j.ins.2021.02.009.
[67] Z. W. Wu, C. T. Chen, and S. H. Huang, “Poisoning attacks against knowledge graph-based recommendation systems using deep reinforcement learning,” Neural Comput. Appl., vol. 34, no. 4, pp. 3097–3115, 2022, doi: 10.1007/s00521-021-06573-8.
[68] J. Zhao, J. Fang, P. Chao, B. Ning, and R. Zhang, “GC-TripRec: Graph contextualized generative network with adversarial learning for trip recommendation,” World Wide Web, vol. 26, no. 5, pp. 2291–2310, 2023, doi: 10.1007/s11280-022-01127-x.
[69] O. Papakyriakopoulos, J. C. M. Serrano, and S. Hegelich, “Political communication on social media: A tale of hyperactive users and bias in recommender systems,” Online Soc. Networks Media, vol. 15, p. 100058, 2020, doi: 10.1016/j.osnem.2019.100058.
[70] Y. Zhao, K. Wang, G. Guo, and X. Wang, “Learning compact yet accurate Generative Adversarial Networks for recommender systems,” Knowledge-Based Syst., vol. 257, 2022, doi: 10.1016/j.knosys.2022.109900.
[71] X. Dai, Z. Wang, J. Xie, T. Yu, and J. C. S. Lui, “Online Learning and Detecting Corrupted Users for Conversational Recommendation Systems,” IEEE Trans. Knowl. Data Eng., vol. 36, no. 12, pp. 8939–8953, 2024, doi: 10.1109/TKDE.2024.3448250.
[72] F. Zhang, P. P. K. Chan, Z. M. He, and D. S. Yeung, “Unsupervised contaminated user profile identification against shilling attack in recommender system,” Intell. Data Anal., vol. 1, no. 1, 2024, doi: 10.3233/IDA-230575.