Skip to main content
Log in

Deep packet: a novel approach for encrypted traffic classification using deep learning

  • Methodologies and Application
  • Published:
Soft Computing Aims and scope Submit manuscript


Network traffic classification has become more important with the rapid growth of Internet and online applications. Numerous studies have been done on this topic which have led to many different approaches. Most of these approaches use predefined features extracted by an expert in order to classify network traffic. In contrast, in this study, we propose a deep learning-based approach which integrates both feature extraction and classification phases into one system. Our proposed scheme, called “Deep Packet,” can handle both traffic characterization in which the network traffic is categorized into major classes (e.g., FTP and P2P) and application identification in which identifying end-user applications (e.g., BitTorrent and Skype) is desired. Contrary to most of the current methods, Deep Packet can identify encrypted traffic and also distinguishes between VPN and non-VPN network traffic. The Deep Packet framework employs two deep neural network structures, namely stacked autoencoder (SAE) and convolution neural network (CNN) in order to classify network traffic. Our experiments show that the best result is achieved when Deep Packet uses CNN as its classification model where it achieves recall of 0.98 in application identification task and 0.94 in traffic categorization task. To the best of our knowledge, Deep Packet outperforms all of the proposed classification methods on UNB ISCX VPN-nonVPN dataset.

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

Access this article

Subscribe and save

Springer+ Basic
EUR 32.99 /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.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others


  • Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Mané D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viégas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2015) TensorFlow: large-scale machine learning on heterogeneous systems., software available from

  • Akhtar N, Mian A (2018) Threat of adversarial attacks on deep learning in computer vision: a survey. arXiv:1801.00553

  • Alipanahi B, Delong A, Weirauch MT, Frey BJ (2015) Predicting the sequence specificities of dna-and rna-binding proteins by deep learning. Nat Biotechnol 33(8):831–838

    Article  Google Scholar 

  • Alshammari R, Zincir-Heywood AN (2011) Can encrypted traffic be identified without port numbers, ip addresses and payload inspection? Comput Netw 55(6):1326–1350

    Article  Google Scholar 

  • Auld T, Moore AW, Gull SF (2007) Bayesian neural networks for internet traffic classification. IEEE Trans Neural Netw 18(1):223–239

    Article  Google Scholar 

  • Bagui S, Fang X, Kalaimannan E, Bagui SC, Sheehan J (2017) Comparison of machine-learning algorithms for classification of vpn network traffic flow using time-related features. J Cyber Secur Technol 1(2):108–126

    Article  Google Scholar 

  • Bengio Y (2009) Learning deep architectures for ai. Found Trends Mach Learn 2(1):1–127

    Article  MathSciNet  Google Scholar 

  • Bengio Y, Lamblin P, Popovici D, Larochelle H (2007) Greedy layer-wise training of deep networks. In: Advances in neural information processing systems, pp 153–160

  • Carlini N, Wagner D (2018) Audio adversarial examples: targeted attacks on speech-to-text. arXiv:1801.01944

  • Caudill M (1987) Neural networks primer, part i. AI Expert 2(12):46–52

    Google Scholar 

  • Chollet F et al (2017) Keras.

  • Chowdhury NMK, Boutaba R (2010) A survey of network virtualization. Comput Netw 54(5):862–876

    Article  Google Scholar 

  • Cover TM, Thomas JA (2006) Elements of information theory. Wiley Series in Telecommunications and Signal Processing. Wiley-Interscience, New Jersy

    MATH  Google Scholar 

  • Crotti M, Dusi M, Gringoli F, Salgarelli L (2007) Traffic classification through simple statistical fingerprinting. ACM SIGCOMM Comput Commun Rev 37(1):5–16

    Article  Google Scholar 

  • Dainotti A, Pescape A, Claffy KC (2012) Issues and future directions in traffic classification. IEEE Netw 26(1):35-40

  • Dingledine R, Mathewson N, Syverson P (2004) Tor: the second-generation onion router. Tech. rep., Naval Research Lab Washington DC

  • dos Santos CN, Gatti M (2014) Deep convolutional neural networks for sentiment analysis of short texts. In: Proceedings of the 25th international conference on computational linguistics (COLING), Dublin, Ireland

  • Du M, Liu N, Hu X (2018) Techniques for interpretable machine learning. arXiv preprint. arXiv:1808.00033

  • Finsterbusch M, Richter C, Rocha E, Muller JA, Hanssgen K (2014) A survey of payload-based traffic classification approaches. IEEE Commun Surv Tutor 16(2):1135–1156

    Article  Google Scholar 

  • Gil GD, Lashkari AH, Mamun M, Ghorbani AA (2016) Characterization of encrypted and vpn traffic using time-related features. In: Proceedings of the 2nd international conference on information systems security and privacy (ICISSP 2016), pp 407–414

  • Hinton G, Deng L, Yu D, Dahl GE, Ar Mohamed, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath TN et al (2012) Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag 29(6):82–97

    Article  Google Scholar 

  • Huang SH, Papernot N, Goodfellow IJ, Duan Y, Abbeel P (2017) Adversarial attacks on neural network policies. arXiv:1702.02284

  • Hubara I, Courbariaux M, Soudry D, El-Yaniv R, Bengio Y (2017) Quantized neural networks: training neural networks with low precision weights and activations. J Mach Learn Res 18(1):6869–6898

    MathSciNet  MATH  Google Scholar 

  • Hubel DH, Wiesel TN (1968) Receptive fields and functional architecture of monkey striate cortex. J Physiol 195(1):215–243

    Article  Google Scholar 

  • Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pp 448–456

  • Khalife J, Hajjar A, Diaz-Verdejo J (2014) A multilevel taxonomy and requirements for an optimal traffic-classification model. Int J Netw Manag 24(2):101–120

    Article  Google Scholar 

  • Kingma D, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint. arXiv:1412.6980

  • Kohout J, Pevný T (2018) Network traffic fingerprinting based on approximated kernel two-sample test. IEEE Trans Inf Forensics Secur.

    Article  Google Scholar 

  • LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444

    Article  Google Scholar 

  • Lee H, Grosse R, Ranganath R, Ng AY (2009) Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: Proceedings of the 26th annual international conference on machine learning, ACM, New York, NY, USA, ICML ’09, pp 609–616

  • Lin DD, Talathi SS, Annapureddy VS (2016) Fixed point quantization of deep convolutional networks. In: Proceedings of the 33rd international conference on international conference on machine learning, vol 48, ICML’16, pp 2849–2858

  • Longadge R, Dongre S (2013) Class imbalance problem in data mining review. arXiv preprint. arXiv:1305.1707

  • Lotfollahi M, Shirali Hossein Zade R, Jafari Siavoshani M, Saberian M (2017) Deep packet: a novel approach for encrypted traffic classification using deep learning. CoRR abs/1709.02656. arXiv:1709.02656

  • Lotfollahi M, Wolf FA, Theis FJ (2018) Generative modeling and latent space arithmetics predict single-cell perturbation response across cell types, studies and species. bioRxiv p 478503

  • Lv J, Zhu C, Tang S, Yang C (2014) Deepflow: hiding anonymous communication traffic in p2p streaming networks. Wuhan Univ J Nat Sci 19(5):417–425

    Article  Google Scholar 

  • Madhukar A, Williamson C (2006) A longitudinal study of p2p traffic classification. In: Modeling, analysis, and simulation of computer and telecommunication systems, 2006. MASCOTS 2006. 14th IEEE international symposium on, IEEE, pp 179–188

  • Montavon G, Samek W, Müller KR (2018) Methods for interpreting and understanding deep neural networks. Digit Signal Process 73:1–15

    Article  MathSciNet  Google Scholar 

  • Moore AW, Papagiannaki K (2005) Toward the accurate identification of network applications. PAM, Springer 5:41–54

    Google Scholar 

  • Moore AW, Zuev D (2005) Internet traffic classification using Bayesian analysis techniques. ACM SIGMETRICS Perform Eval Rev ACM 33:50–60

    Article  Google Scholar 

  • Moore A, Zuev D, Crogan M (2013) Discriminators for use in flow-based classification. Tech. rep

  • Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830

    MathSciNet  MATH  Google Scholar 

  • Perera P, Tian YC, Fidge C, Kelly W (2017) A comparison of supervised machine learning algorithms for classification of communications network traffic. In: Neural information processing. Springer, Cham, Lecture Notes in Computer Science, pp 445–454.

  • Prechelt L (1998) Early stopping-but when? Neural networks: tricks of the trade. Springer, pp 55–69

  • Qi Y, Xu L, Yang B, Xue Y, Li J (2009) Packet classification algorithms: from theory to practice. In: INFOCOM 2009, IEEE, IEEE, pp 648–656

  • Samek W, Wiegand T, Müller KR (2018) Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models. ITU J ICT Discov Special Issue 1 Impact Artif Intell (AI) Commun Netw Serv 1(1):39–48

    Google Scholar 

  • Sen S, Spatscheck O, Wang D (2004) Accurate, scalable in-network identification of p2p traffic using application signatures. In: Proceedings of the 13th international conference on world wide web, ACM, New York, NY, USA, pp 512–521

  • Sherry J, Lan C, Popa RA, Ratnasamy S (2015) Blindbox: deep packet inspection over encrypted traffic. ACM SIGCOMM Comput Commun Rev ACM 45:213–226

    Article  Google Scholar 

  • Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint. arXiv:1409.1556

  • Socher R, Perelygin A, Wu JY, Chuang J, Manning CD, Ng AY, Potts CP (2013) Recursive deep models for semantic compositionality over a sentiment treebank. In: EMNLP

  • Sun R, Yang B, Peng L, Chen Z, Zhang L, Jing S (2010) Traffic classification using probabilistic neural networks. In: Natural computation (ICNC), 2010 sixth international conference on, IEEE, vol 4, pp 1914–1919

  • Ting H, Yong W, Xiaoling T (2010) Network traffic classification based on kernel self-organizing maps. In: Intelligent computing and integrated systems (ICISS), 2010 international conference on, IEEE, pp 310–314

  • Vanhoucke V, Senior A, Mao MZ (2011) Improving the speed of neural networks on cpus. In: Deep learning and unsupervised feature learning workshop, NIPS 2011

  • Velan P, Čermák M, Čeleda P, Drašar M (2015) A survey of methods for encrypted traffic classification and analysis. Int J Netw Manag 25(5):355–374

    Article  Google Scholar 

  • Vincent P, Larochelle H, Bengio Y, Manzagol PA (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning, ACM, pp 1096–1103

  • Wang Z (2015) The applications of deep learning on traffic identification. BlackHat, USA

    Google Scholar 

  • Wang X, Parish DJ (2010) Optimised multi-stage tcp traffic classifier based on packet size distributions. In: Communication theory, reliability, and quality of service (CTRQ), 2010 third international conference on, IEEE, pp 98–103

  • Wang W, Zhu M, Wang J, Zeng X, Yang Z (2017) End-to-end encrypted traffic classification with one-dimensional convolution neural networks. In: Intelligence and security informatics (ISI), 2017 IEEE international conference on, IEEE, pp 43–48

  • Yamansavascilar B, Guvensan MA, Yavuz AG, Karsligil ME (2017) Application identification via network traffic classification. In: Computing, networking and communications (ICNC), 2017 international conference on, IEEE, pp 843–848

  • Yeganeh SH, Eftekhar M, Ganjali Y, Keralapura R, Nucci A (2012) Cute: traffic classification using terms. In: Computer communications and networks (ICCCN), 2012 21st international conference on, IEEE, pp 1–9

  • Yosinski J, Clune J, Nguyen AM, Fuchs TJ, Lipson H (2015) Understanding neural networks through deep visualization. arXiv:1506.06579

  • Yuan X, He P, Zhu Q, Bhat RR, Li X (2017) Adversarial examples: attacks and defenses for deep learning. arXiv:1712.07107

  • Zhang C, Li P, Sun G, Guan Y, Xiao B, Cong J (2015) Optimizing fpga-based accelerator design for deep convolutional neural networks. In: Proceedings of the 2015 ACM/SIGDA international symposium on field-programmable gate arrays, ACM, pp 161–170

Download references


The authors would like to thank Farzad Ghasemi and Mehdi Kharrazi for their valuable discussions and feedback.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Mahdi Jafari Siavoshani.

Ethics declarations

Conflict of interest

Mohammad Lotfollahi, Mahdi Jafari Siavoshani, Ramin Shirali Hossein Zade, and Mohammdsadegh Saberian declare that they have no conflict of interest

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Communicated by V. Loia.

Publisher's Note

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



Here, in this section, we present all of the hyper-parameters of the proposed SAE and CNN for the traffic characterization and application identification tasks. These parameters are stated in Tables 9, 10, 11 and 12.

In the following, to have more compact tables, we have used some abbreviations, namely FC stands for “Fully connected,” NoF stands for “Number of Features,” DO stands for “Dropout,” BN stands for “Batch Normalization,” NL stands for “Nonlinearity,” Str stands for “Strides,” and Kl stands for “Kernel.”

Table 9 SAE detailed architecture for the application identification task
Table 10 SAE detailed architecture for the traffic characterization task
Table 11 CNN detailed architecture for the application identification task
Table 12 CNN detailed architecture for the traffic characterization task

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lotfollahi, M., Jafari Siavoshani, M., Shirali Hossein Zade, R. et al. Deep packet: a novel approach for encrypted traffic classification using deep learning. Soft Comput 24, 1999–2012 (2020).

Download citation

  • Published:

  • Issue Date:

  • DOI: