Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Recent Advances in Electrical & Electronic Engineering
  4. Volume 18, Issue 2
  5. Article
Volume 18, Issue 2
  • ISSN: 2352-0965
  • E-ISSN: 2352-0973

Abstract

Introduction

Recommender systems serve as a powerful tool to address the challenges of information overload by delivering personalized recommendations. However, their susceptibility to profile injection or shilling attacks poses a significant threat. Malicious entities can introduce fabricated profiles into the database of users to manipulate the popularity of specific items, subsequently influencing prediction outcomes.

Methods

Detecting and mitigating the impact of such attacks is critical for preserving recommendation accuracy and user trust. The primary objective of this study is to develop an integrated framework for robust shilling attack detection and data sparsity mitigation in recommendation systems. This approach aims to make the system more resistant to manipulative attacks and improve recommendation quality, especially when dealing with limited data. In this paper, Skew Deviation Bias (SDB), is a novel metric that gauges the skewness within rating distributions, enabling the identification of both fabricated shilling profiles and the anomalous rating behaviors exhibited by attackers. Building upon this foundation, SDB is integrated with other statistical metrics like Rating deviation from the mean agreement (RDMA), Weighted deviation from the mean agreement (WDMA), Weighted degree of agreement (WDA), and length variance. This research investigates the impact of incorporating SDB alongside existing attributes in countering various attack scenarios, including random, average, and bandwagon attacks.

Results

Extensive experiments are conducted to compare the effectiveness of SDB when integrated with existing attributes against scenarios employing only existing attributes. These experiments cover a range of attack sizes while maintaining a fixed 50% filler size. The results of thorough comparative analyses demonstrate the consistent superiority of the SDB-integrated approach, resulting in higher accuracy across all attack types compared to scenarios using only existing attributes. Notably, the random attack scenario shows the most significant accuracy improvement among the evaluated scenarios.

Conclusion

The approach achieves a detection accuracy of 97.08% for random shilling attacks, affirming its robustness. Furthermore, in the context of data sparsity, the approach notably enhances recommendation quality.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/raeeng/10.2174/0123520965265325231206094044
2024-01-24
2025-06-24

  • From This Site

    /content/journals/raeeng/10.2174/0123520965265325231206094044
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. AdomaviciusG. TuzhilinA. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions.IEEE Trans. Knowl. Data Eng.200517673474910.1109/TKDE.2005.99
     [Google Scholar]
  2. ZhouTao Emergence of scale-free leadership structure in social recommender systems.PLoS One2011e2064810.1371/journal.pone.0020648
     [Google Scholar]
  3. BurkeR. Classification features for attack detection in collaborative recommender systemsProceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining August 2006Pages 542–54710.1145/1150402.1150465
     [Google Scholar]
  4. LamS.K. RiedlJ. Shilling recommender systems for fun and profitProceedings of the 13th International Conference on World Wide Web May 2004Pages 393–40210.1145/988672.988726
     [Google Scholar]
  5. MehtaB. HofmannT. NejdlW. Robust collaborative filteringProceedings of the 2007 ACM Conference on Recommender systems ACM2007 pp. 49-56.10.1145/1297231.1297240
     [Google Scholar]
  6. FengG. “Robust recommendation algorithm based on metadata fusion.” International Journal of U-& E-Service.Sci. Technol201476
     [Google Scholar]
  7. BhaumikR. Securing collaborative filtering against malicious attacks through anomaly detectionProceedings of the 4th workshop on intelligent techniques for web personalization (ITWP’06)Boston, Vol. 6, 2006
     [Google Scholar]
  8. MehtaB. NejdlW. Attack-resistant collaborative filteringProceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval SIGIR2008, Singapore, July 20-24, 2008.
     [Google Scholar]
  9. Burke, Robin, et al. Segment-based injection attacks against collaborative filtering recommender systems.Fifth IEEE International Conference on Data Mining (ICDM'05). IEEE2005
     [Google Scholar]
  10. MobasherBamshad Toward trustworthy recommender systems: An analysis of attack models and algorithm robustnessACM Transactions on Internet Technologyvol. 7, no. 4, pp. 23-es, 200710.1145/1278366.1278372
     [Google Scholar]
  11. ChengZ. HurleyN. Effective diverse and obfuscated attacks on model-based recommender systemsProceedings of the third ACM conference on Recommender systemsOctober 2009Pages 141–14810.1145/1639714.1639739
     [Google Scholar]
  12. Carrer-NetoW. Hernández-AlcarazM.L. Valencia-GarcíaR. García-SánchezF. Social knowledge-based recommender system. Application to the movies domain.Expert Syst. Appl.20123912109901100010.1016/j.eswa.2012.03.025
     [Google Scholar]
  13. WilliamsC.A. MobasherB. BurkeR. Defending recommender systems: Detection of profile injection attacks.Serv. Oriented Comput. Appl.20071315717010.1007/s11761‑007‑0013‑0
     [Google Scholar]
  14. XuY. ZhangF. Detecting shilling attacks in social recommender systems based on time series analysis and trust features.Knowl. Base. Syst.2019178254710.1016/j.knosys.2019.04.012
     [Google Scholar]
  15. BatmazZ. YilmazelB. KaleliC. Shilling attack detection in binary data: A classification approach.J. Ambient Intell. Humaniz. Comput.20201162601261110.1007/s12652‑019‑01321‑2
     [Google Scholar]
  16. LeeJ.S. ZhuD. Shilling attack detection—a new approach for a trustworthy recommender system.INFORMS J. Comput.201224111713110.1287/ijoc.1100.0440
     [Google Scholar]
  17. CaiH. ZhangF. Detecting shilling attacks in recommender systems based on analysis of user rating behavior.Knowl. Base. Syst.2019177224310.1016/j.knosys.2019.04.001
     [Google Scholar]
  18. MehtaB. NejdlW. Unsupervised strategies for shilling detection and robust collaborative filtering.User Model. User-adapt. Interact.2009191-2659710.1007/s11257‑008‑9050‑4
     [Google Scholar]
  19. WuZ. HySAD: A semi-supervised hybrid shilling attack detector for trustworthy product recommendationProceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data miningAugust 2012Pages 985–99310.1145/2339530.2339684
     [Google Scholar]
  20. ZhangF. QuY. XuY. WangS. Graph embedding-based approach for detecting group shilling attacks in collaborative recommender systems.Knowl. Base. Syst.202019910598410.1016/j.knosys.2020.105984
     [Google Scholar]
  21. YuH. Detecting group shilling attacks in recommender systems based on maximum dense subtensor mining2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)28-30 June 2021, Dalian, China, pp. 644-64810.1109/ICAICA52286.2021.9498095
     [Google Scholar]
  22. CaiH. ZhangF. An unsupervised approach for detecting group shilling attacks in recommender systems based on topological potential and group behavior features.Secur. Commun. Netw.20212021118
     [Google Scholar]
  23. ZhangF. WangS. Detecting group shilling attacks in online recommender systems based on bisecting k-means clustering.IEEE Trans. Comput. Soc. Syst.2020751189119910.1109/TCSS.2020.3013878
     [Google Scholar]
  24. TianY. PanL. “Predicting short-term traffic flow by long short-term memory recurrent neural network.” 2015 IEEE international conference on smart city/SocialCom/SustainCom (SmartCity).IEEE2015
     [Google Scholar]
  25. Tong, Chao, et al. A shilling attack detector based on convolutional neural network for collaborative recommender system in social aware network.The Computer Journal 61.7 (2018): 949-95810.1093/comjnl/bxy008
     [Google Scholar]
  26. QuanqiangZhou Jinxia Wu Liangliang Duan. Recommendation attack detection based on deep learning.Journal of Information Security and Applications52 (2020): 10249310.1016/j.jisa.2020.102493
     [Google Scholar]
  27. CaiH. ZhangF. BS-SC: An unsupervised approach for detecting shilling profiles in collaborative recommender systems.IEEE Trans. Knowl. Data Eng.20213341375138810.1109/TKDE.2019.2946247
     [Google Scholar]
  28. YangZ. SunQ. ZhangY. Probabilistic inference and trustworthiness evaluation of associative links toward malicious attack detection for online recommendations.IEEE Trans. Depend. Secure Comput.2020192110.1109/TDSC.2020.3023114
     [Google Scholar]
  29. PanagiotakisC. PapadakisH. FragopoulouP. Unsupervised and supervised methods for the detection of hurriedly created profiles in recommender systems.Int. J. Mach. Learn. Cybern.20201192165217910.1007/s13042‑020‑01108‑4
     [Google Scholar]
  30. KayaT.T. YalcinE. KaleliC. A novel classification-based shilling attack detection approach for multi-criteria recommender systems.Comput. Intell.202339349952810.1111/coin.12579
     [Google Scholar]
  31. HaoY. MengG. WangJ. ZongC. A detection method for hybrid attacks in recommender systems.Inf. Syst.202311410215410.1016/j.is.2022.102154
     [Google Scholar]
  32. ChenX. DengX. HuangC. ShinH. Detection of trust shilling attacks in recommender systems.IEICE Trans. Inf. Syst.2022E105D1239124210.1587/transinf.2021EDL8094
     [Google Scholar]
  33. AlonsoS. BobadillaJ. OrtegaF. MoyaR. Robust modelbased reliability approach to tackle shilling attacks in collaborative filtering recommender systems.IEEE Access20197417824179810.1109/ACCESS.2019.2905862
     [Google Scholar]
  34. ZhangF. ZhangZ. ZhangP. WangS. UD-HMM: An unsupervised method for shilling attack detection based on hidden Markov model and hierarchical clustering.Knowl. Base. Syst.201814814616610.1016/j.knosys.2018.02.032
     [Google Scholar]
  35. ZhangF. ChenH. An ensemble method for detecting shilling attacks based on ordered item sequences.Secur. Commun. Netw.20169768069610.1002/sec.1389
     [Google Scholar]
  36. ShaoC. SunY. Shilling attack detection for collaborative recommender systems: A gradient boosting method.Math. Biosci. Eng.20221977248727110.3934/mbe.2022342 35730305
     [Google Scholar]
  37. GaoJ. Shilling attack detection scheme in collaborative filtering recommendation system based on recurrent neural networkProceedings of the 2020 Future of Information and Communication Conference (FICC)Springer International PublishingVolume 1 2020, (pp.634-644)10.1007/978‑3‑030‑39445‑5_46
     [Google Scholar]
  38. ZhouW. WenJ. XiongQ. GaoM. ZengJ. SVM-TIA a shilling attack detection method based on SVM and target item analysis in recommender systems.Neurocomputing201621019720510.1016/j.neucom.2015.12.137
     [Google Scholar]
  39. ZhouWei Shilling attack detection for recommender systems based on the credibility of group users and rating time seriep. e0196533, 2018.PloS one, p. e0196533201810.1371/journal.pone.0196533
     [Google Scholar]
  40. LvF. SDM: Sequential deep matching model for online largescale recommender systemProceedings of the 28th ACM International Conference on Information and Knowledge ManagementNovember 2019 Pages 2635–2643.10.1145/3357384.3357818
     [Google Scholar]
/content/journals/raeeng/10.2174/0123520965265325231206094044
Loading
Enhancing Recommendation Systems with Skew Deviation Bias for Shilling Attack Detection
Recent Advances in Electrical & Electronic Engineering 18, 212 (2025); https://doi.org/10.2174/0123520965265325231206094044
/content/journals/raeeng/10.2174/0123520965265325231206094044
/content/journals/raeeng/10.2174/0123520965265325231206094044
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): collaborative filtering; recommender system; SBD; shilling attack; Skewed deviation bias; support vector machine

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test