Skip to main content

Advertisement

Springer Nature Link
Log in

A preliminary exploration of the T cells multilayer immune tolerance model

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

The negative selection algorithm (NSA), inspired by human immunity, has the advantages of being adaptable and not requiring prior knowledge, so it is increasingly used across various industries. To address issues related to security detection, intrusion detection, anomaly detection, fault detection, and other industry-related problems, various improvements have been made; however, the false positive (FP) problem remains unresolved. The NSA comprises the detector generation stage and the detection stage. Thus far, improvements have concentrated on the first stage to create a flawless detector set, yet no researcher has considered enhancing the second linear detection stage, which leads to the FP. This paper re-examines the current advancements in biological immunology, utilizes the multilayer immune tolerance mechanism to improve the NSA, and proposes the multilayer immune tolerance (MIT) method based on the NSA to decrease FP. This method is divided into three layers. The first layer generates the detector set through the NSA. The second layer tolerates or filters out escaped and unfunctional detectors by simulating the ignorance mechanism and the co-stimulation mechanism, thereby producing the activated detectors. Specifically, the activating set derived from the testing set is clustered using the k-means method, and the generated detectors and the clusters are utilized to obtain pre-activated detectors through the concentration-checking based on MIT (CC-MIT) algorithm, with activated detectors being determined by the co-stimulation based on MIT (CS-MIT) algorithm. In the third layer, these activated detectors are evaluated using the positive selection algorithm. Those within the activated range of detectors are classified as abnormal, while others are considered normal. This method significantly reduces the occurrence of unfunctional or escaped detectors, thereby greatly decreasing FP and enhancing detection precision. The effectiveness of the proposed MIT method and the selection of the related parameters is validated through experiments comparing it with the NSA algorithm. Furthermore, the progress of this method is illustrated through comparisons with well-regarded algorithms known for their efficacy in anomaly detection, especially in apparently improving precision.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Algorithm 1
Fig. 5
Algorithm 2
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Data availability

No datasets were generated or analysed during the current study.

References

  1. Zhou W, Liang Y, Dong H, Tan C, Xiao Z, Liu W (2017) A numerical differentiation based dendritic cell model. In: 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI), pp. 1092–1098. IEEE

  2. Saurabh P, Verma B (2023) Negative selection in anomaly detection-a survey. Comput Sci Rev 48:100557

    Article  MathSciNet  MATH  Google Scholar 

  3. Althalji A, Khawatmi S, Khatib M (2023) Improving the security of aodv protocol using v-detector algorithm. Int J Comput Appl 975:8887

    MATH  Google Scholar 

  4. Ren Y, Wang X, Zhang C (2020) A novel fault diagnosis method based on improved negative selection algorithm. IEEE Trans Instrum Meas 70:1–8

    MATH  Google Scholar 

  5. Wen C, Changzhi W (2022) Combine labeled and unlabeled data for immune detector training with label propagation. Knowl-Based Syst 236:107661

    Article  MATH  Google Scholar 

  6. Gu M, Li D, Liu J, Shan W, Liu S (2024) A negative selection algorithm with hypercube interface detectors for anomaly detection. Appl Soft Comput 154:111339

    Article  MATH  Google Scholar 

  7. Singh K, Kaur L, Maini R (2022) A survey of intrusion detection techniques based on negative selection algorithm. Int J Syst Assur Eng Manag 1–11

  8. Duru C, Ladeji–Osias J, Wandji K, Otily T, Kone R (2022) A review of human immune inspired algorithms for intrusion detection systems. In: 2022 IEEE World AI IoT Congress (AIIoT). IEEE, pp 364–371

  9. Peng L, Liang Y, Yang H (2024) Improved v-detector algorithm based on bagging for earthquake prediction with faults. J Supercomput 80(16):24605–24637

    Article  MATH  Google Scholar 

  10. Forrest S, Perelson AS, Allen L, Cherukuri R (1994) Self-nonself discrimination in a computer. In: Proceedings of 1994 IEEE Computer Society Symposium on Research in Security and Privacy. IEEE, pp 202–212

  11. Kodati S, Sreekanth N, Sarma K, Reddy PCS, Saxena A, Narasaiah BP (2023) Ensemble framework of artificial immune system based on network intrusion detection system for network security sustainability. In: E3S Web of Conferences, vol 430. EDP Sciences, p 01070

  12. Ma M, Yang G, He J, Fang W (2024) An adaptive detection framework based on artificial immune for iot intrusion detection system. Appl Soft Comput 166:112152

    Article  MATH  Google Scholar 

  13. Chen J, He J, Li W, Fang W, Lan X, Ma W, Li T (2024) A hierarchical unmanned aerial vehicle network intrusion detection and response approach based on immune vaccine distribution. IEEE Internet Things J

  14. Yang G, Wang L, Yu R, He J, Zeng B, Wu T (2023) A modified gray wolf optimizer-based negative selection algorithm for network anomaly detection. Int J Intell Syst 2023(1):8980876

    Article  MATH  Google Scholar 

  15. Huang H, Liu N, Chen D, Yang Q, Huang X (2022) Research on the intrusion detection model of underwater sensor networks. J Sensors 2022(1):2323747

    MATH  Google Scholar 

  16. Li B, Chang Y, Huang H, Li W, Li T, Chen W (2023) Artificial immunity based distributed and fast anomaly detection for industrial internet of things. Futur Gener Comput Syst 148:367–379

    Article  MATH  Google Scholar 

  17. Gupta KD, Dasgupta D (2021) Using negative detectors for identifying adversarial data manipulation in machine learning. In: 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1–8

  18. Sompayrac LM (2022) How the immune system works. Wiley, Hoboken

    MATH  Google Scholar 

  19. Yatim KM, Lakkis FG (2015) A brief journey through the immune system. Clin J Am Soc Nephrol 10(7):1274–1281

    Article  MATH  Google Scholar 

  20. Waldmann H (2016) Mechanisms of immunological tolerance. Clin Biochem 49(4–5):324–328

    Article  MATH  Google Scholar 

  21. Mills CD, Ley K, Buchmann K, Canton J (2015) Sequential immune responses: the weapons of immunity. J Innate Immun 7(5):443–449

    Article  MATH  Google Scholar 

  22. Aarthy R, Muthupriya V, Balaji G (2024) Detection of bone cancer based on a four-phase framework generative deep belief neural network in deep learning. Alex Eng J 109:394–407

    Article  MATH  Google Scholar 

  23. Owen RD (1945) Immunogenetic consequences of vascular anastomoses between bovine twins. Science 102(2651):400–401

    Article  Google Scholar 

  24. Schwartz RH (2012) Historical overview of immunological tolerance. Cold Spring Harb Perspect Biol 4(4):006908

    Article  MATH  Google Scholar 

  25. Gammon JM, Jewell CM (2019) Engineering immune tolerance with biomaterials. Adv Healthc Mater 8(4):1801419

    Article  Google Scholar 

  26. Yang L, Jin R, Lu D, Ge Q (2020) T cell tolerance in early life. Front Immunol 11:576261

    Article  MATH  Google Scholar 

  27. Suhrkamp I, Scheffold A, Heine G (2023) T-cell subsets in allergy and tolerance induction. Eur J Immunol 53(10):2249983

    Article  MATH  Google Scholar 

  28. Bluestone JA, McKenzie BS, Beilke J, Ramsdell F (2023) Opportunities for treg cell therapy for the treatment of human disease. Front Immunol 14:1166135

    Article  Google Scholar 

  29. Cho E, Han S, Eom HS, Lee S-J, Han C, Singh R, Kim S-H, Park B-M, Kim B-G, Kim YH (2023) Cross-activation of regulatory t cells by self antigens limits self-reactive and activated cd8+ t cell responses. Int J Mol Sci 24(18):13672

    Article  MATH  Google Scholar 

  30. Brown CC, Rudensky AY (2023) Spatiotemporal regulation of peripheral t cell tolerance. Science 380(6644):472–478

    Article  MATH  Google Scholar 

  31. Wortel IM, Keşmir C, Boer RJ, Mandl JN, Textor J (2020) Is t cell negative selection a learning algorithm? Cells 9(3):690

    Article  MATH  Google Scholar 

  32. Saxena V, Li L, Paluskievicz C, Kasinath V, Bean A, Abdi R, Jewell CM, Bromberg JS (2019) Role of lymph node stroma and microenvironment in t cell tolerance. Immunol Rev 292(1):9–23

    Article  Google Scholar 

  33. Hofmeyr S (2004) The implications of immunology for secure systems design. Comput Secur 23(6):453–455

    Article  MATH  Google Scholar 

  34. Li Z, Li T (2022) Using known nonself samples to improve negative selection algorithm. Appl Intell 52(1):482–500

    Article  MATH  Google Scholar 

  35. Zhou C, Paffenroth RC (2017) Anomaly detection with robust deep autoencoders. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 665–674

  36. Chen Z, Yeo CK, Lee BS, Lau CT (2018) Autoencoder-based network anomaly detection. In: 2018 Wireless Telecommunications Symposium (WTS). IEEE, pp 1–5

Download references

Acknowledgements

The authors want to thank the National Natural Science Foundation of China-http://www.nsfc.gov.cn for the support through Grants Number 62202147.

Author information

Authors and Affiliations

  1. School of Computer Science, Wuhan University, No.299 Bayi Road, Wuchang District, Wuhan, 430072, Hubei, China

    Lu Peng & Yiwen Liang

  2. College of Information Science and Engineering, Wuchang Shouyi University, No.22 Nanli Road, Hongshan District, Wuhan, 430064, Hubei, China

    Lu Peng

  3. School of Computer Science, Hubei University of Technology, No.28 Nanli Road, Hongshan District, Wuhan, 430068, Hubei, China

    Wen Zhou

  4. School of Computer Science, Hubei University of Education, No.129, Gaoxin 2nd Road, Hongshan District, Wuhan, 430205, Hubei, China

    He Yang

  5. School of Computer Science and Information Engineering, Wuhan Railway Vocational College of Technology, No.1, Canglong Avenue, Jiangxia District, Wuhan, 430205, Hubei, China

    Fan Yang

Authors
  1. Lu Peng
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Yiwen Liang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Wen Zhou
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. He Yang
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Fan Yang
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Lu Peng and Wen Zhou wrote the main manuscript, while Yiwen Liang and He Yang supervised the project, edited the review, and acquired funding. Fan Yang prepared Figures 6-12. All authors reviewed the manuscript.

Corresponding author

Correspondence to Yiwen Liang.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Peng, L., Liang, Y., Zhou, W. et al. A preliminary exploration of the T cells multilayer immune tolerance model. J Supercomput 81, 565 (2025). https://doi.org/10.1007/s11227-025-07059-3

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11227-025-07059-3

Keywords