Clustered negative selection algorithm and fruit fly optimization for email spam detection

  • Ramdane ChikhEmail author
  • Salim Chikhi
Original Research


At present, spam is an actual and increasing problem that compromises email communications across the world. Thus, several solutions have been proposed to stop or reduce the amount of this threat. However, methods based on negative selection algorithm (NSA) lack continuous adaptability and suffer from low detection performance. Moreover, these methods require a large number of detectors to cover all non-self spaces. Thus, this study proposes a new e-mail detection approach based on an improved NSA called combined clustered NSA and fruit fly optimization (CNSA–FFO). The system combines actual NSA with k-means clustering and FFO to enhance the efficiency of classic NSA. Experiments results in spam benchmark show that the performance of CNSA–FFO is better than the classic NSA and NSA–PSO, especially in terms of detection accuracy, positive prediction, and computational complexity.


Artificial immune system Negative selection algorithm E-mail spam Fruit fly optimization K-means clustering 


  1. Abdolahnezhad MR, Banirostam T (2016) Improved negative selection algorithm for email spam detection application. Int J Adv Res Electron Commun Eng 5:956–960Google Scholar
  2. Aiqiang X, Yong L, Xiuli Z, chunying Y, Tingjun L (2011) Optimization and application of real-valued negative selection algorithm. Procedia Eng 23:241–246CrossRefGoogle Scholar
  3. Bo X, Wen-Jing G (2014) Fruit fly optimization algorithm. In: Innovative computational intelligence: a rough guide to 134 clever algorithms, Part II, vol 62. Springer, Berlin, pp 167–170Google Scholar
  4. Chen W, Li T, Liu XJ, Zhang B (2013) A negative selection algorithm based on hierarchical clustering of self set. In: Information sciences, vol 56. Springer and Science, China, pp 1–13Google Scholar
  5. Dasgupta D, Yu S, Nino F (2011) Recent advances in artificial immune systems. Soft Comput 11:1574–1587CrossRefGoogle Scholar
  6. Dong L, Shulin L, Hongli Z (2016) A boundary-fixed negative selection algorithm with online adaptive learning under small samples for anomaly detection. In: Engineering Applications of Artificial Intelligence, vol 50. Elsevier, pp 93–105Google Scholar
  7. De Castro LN, Timmis JI (2003) Artificial immune systems as a novel soft computing paradigm. Soft Comput 7:526–544CrossRefGoogle Scholar
  8. Forrest S, Perelson A, Allen L, Cherukuri R (1994) Self-nonself discrimination in a computer. In: PW IEEE Symp on Research in Security and Privacy, IEEECrossRefGoogle Scholar
  9. Gang C, Wenjian L, ao Z (1979) Evolutionary clustering with differential evolution. IEEE congress on evolutionary computation (CEC), IEEE, vol 28, 1, pp 100–108Google Scholar
  10. Gonzalez F, Dasgupta D, Kozma R (2002) Combiningnegativeselectionandclassificationtechniquesforanomalydetection. In: Proceedings of the congress on evolutionary computation (CEC-2002), IEEE, 0-7803-7282-4Google Scholar
  11. Gonzalez F, Dasgupta D, Niño LF (2003) A randomized real-valued negative selection algorithm. In: ICARIS 2003, Computer Science, vol 2787. Springer, pp 261–272Google Scholar
  12. Guiyang L, Tao L, Jie Z, Haibo l (2010) An outlier robust negative selection algorithm inspired by immune suppression. J Comput 5(9)Google Scholar
  13. Han JY, Liu CZ (2013) Fruit fly optimization algorithm with adaptive mutation. Appl Res Comput 30:1–6 (in Chinese) Google Scholar
  14. Hartigan JA, Wong MA (1979) A k-means clustering algorithm. J R Stat Soc Ser C (Appl Statis)Google Scholar
  15. Hazim I, Mesut G (2015) A survey on fruit fly optimization algorithm. In: 11th international conference on signal-image technology and internet-based systems, IEEE computer societyGoogle Scholar
  16. Hopkins M et al (1999) UCI machine learning repository: spam base data set. Hewlett-Packard Labs.
  17. Ismaila I, Ali S (2014) Improved email spam detection model with negative selection algorithm and particle swarm optimization. Appl Soft Comput 22:11–27CrossRefGoogle Scholar
  18. Ismaila I, Ali S, Sigeru O (2014) Hybrid email spam detection model with negative selection algorithm and differential evolution. Eng Appl Artif Intell 28:97–110CrossRefGoogle Scholar
  19. Ismaila I, Ali S, Ngoc TN, Sigeru O, Ondrej K, Kamil K, Marek P (2015) A combined negative selection algorithm–particle swarm optimization for an email spam detection system. Eng Appl Artif Intell J 39:33–44CrossRefGoogle Scholar
  20. Jie Z, Wenjian L (2014) EvoSeedRNSAII: an improved evolutionary algorithm for generating detectors in the real-valued negative selection algorithms. Appl Soft Comput 19:18–30CrossRefGoogle Scholar
  21. Jie Z, Wenjian L, Baoliang X (2009) Generating an approximately optimal detector set by evolving random seeds. In: The eighth IEEE international conference on dependable, autonomic and secure computing, Chengdu, China, IEEE, 978-0-7695-3929-4409Google Scholar
  22. Jinquan Z, Xiaojie L, Tao L, Caiming L, Lingxi P, Feixian S (2009) A self-adaptive negative selection algorithm used for anomaly detection. Prog Nat Sci 19:261–266CrossRefGoogle Scholar
  23. Kim JW (2002) Integrating artificial immune algorithms for intrusion detection. PhD Thesis, University College LondonGoogle Scholar
  24. Li D, Liu S, Zhang H (2015) A negative selection algorithm with online adaptive learning under small samples for anomaly detection. Neuro Comput J 149:515–525Google Scholar
  25. Li D, Liu S, Zhang H (2016) A boundary-fixed negative selection algorithm with online adaptive learning under small samples for anomaly detection. Eng Appl Artif Intell 50:93–105CrossRefGoogle Scholar
  26. Lin C, Dechang P, Chuanming C (2015) BIORV-NSA: bidirectional inhibition optimization r-variable negative selection algorithm and its application. Appl Soft Comput 32:544–552CrossRefGoogle Scholar
  27. Liu Y, Wang X, Li Y (2012) A modified fruit-fly optimization algorithm aided PID controller designing. IEEE 10th world congress on intelligent control and automation, Beijing, ChinaGoogle Scholar
  28. Maoguo G, Jian Z, Jingjing M, Licheng J (2012) An efficient negative selection algorithm with further training for anomaly detection. Knowl Based Syst 30:185–191CrossRefGoogle Scholar
  29. Pan WT (2011) A new fruit fly optimization algorithm: taking the financial distress model as an example. Knowl Based Syst ACM 26:69–74CrossRefGoogle Scholar
  30. Puteh M, Hamdan AR, Omar K, Bakar A (2008) Flexible immune network recognition system for mining heterogeneous data. In: 7th international conference on artificial immune systems, Phuket, Thailand, SpringerGoogle Scholar
  31. Raed AZ, Adel H (2013) Genetic optimized artificial immune system in spam detection: a review and a model. Artif Intell Rev 40:305–377CrossRefGoogle Scholar
  32. Ramdane C, Chikhi S (2014) A new negative selection algorithm for adaptive network intrusion detection system. Int J Inf Secur Priv 8(4):1–25CrossRefGoogle Scholar
  33. Shelly XW, Wolfgang B (2010) The use of computational intelligence in intrusion detection systems: a review. Appl Soft Comput 10:1–35CrossRefGoogle Scholar
  34. Vieira LN, Lima BSLPD, Jacop BP (2008) Optimization of steel catenary risers for offshore oil production using artificial immune system. In: 7th international conference on artificial immune systems (ICARIS 2008), Phuket, Thailand, SpringerGoogle Scholar
  35. Wang B, Zhang S (2007) A new intrusion detection method based on artificial immune system. In: Network and parallel computing workshops, IEEE, pp 91–98Google Scholar
  36. Wang L, Zheng X-L, Wang S-Y (2013) A novel binary fruit fly optimization algorithm for solving the multidimensional knapsack problem. Knowl Based Syst 48:17–23CrossRefGoogle Scholar
  37. Wen C, Xiaoming D, Tao L, Tao Y (2014) Negative selection algorithm based on grid file of the feature space. Knowl Based Syst 56:26–35CrossRefGoogle Scholar
  38. Wu P, Zheng X (2012) An improved variable-radius real-valued negative selection algorithm. J Inf Comput Sci 16:4713–4720Google Scholar
  39. Xiao X, Li T, Zhang R (2015) An immune optimization based real-valued negative selection algorithm. Appl Intell J 42:289–302CrossRefGoogle Scholar
  40. Zhenga X, Zhoua Y, Fangb Y (2013) Dual negative selection algorithm based on pattern recognition receptor theory and its application in two-class data classification. J Comput 8:1951–1959Google Scholar
  41. Zhou J, Dasgupta D (2009) V-detector: an efficient negative selection algorithm with“probably adequate” detector coverage. Inf Sci 179:1390–1406CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2017

Authors and Affiliations

  1. 1.Faculty of TechnologySétif 1 UniversitySétifAlgeria
  2. 2.MISC LaboratoryConstantine 2 UniversityConstantineAlgeria

Personalised recommendations