Semi-Supervised Encrypted Traffic Classification With Deep Convolutional Generative Adversarial Networks

Iliyasu, Auwal Sani; Deng, Hongbo

doi:10.1109/access.2019.2962106

Cited by 82 publications

(31 citation statements)

References 14 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As explained previously, our approach differs in the kind of features that we select from the dataset, as we ignore all the header data. Finally, Iliyasu and Deng develop a semisupervised method using Deep Convolutional Generative Adversarial Networks [29]. In general, they achieve lower accuracies on the classification problem relative to other works, however they can work with small labeled datasets.…”

Section: Related Workmentioning

confidence: 99%

Packet Length Spectral Analysis for IoT Flow Classification Using Ensemble Learning

Cirillo

2020

IEEE Access

View full text Add to dashboard Cite

With the proliferation of ubiquitous and autonomous devices for sensing, control, monitoring and conditioning, the Internet of Things (IoT) holds a great potential for the development of innovative applications. At the same time, network operators must support these devices with differentiated services, which rely on the ability to automatically recognize and classify the nature of the communication flows. In this paper, we present a supervised learning approach to discriminate between IoT and non-IoT traffic, and to determine the class of the device originating the packet flows. We make use of a reduced set of features based on the spectral analysis of the packet lengths of a flow, and evaluate an ensemble learning algorithm that uses a Random Forest classifier. We first discuss the datasets and the procedure that we use to extract the features, with examples from different devices. The evaluation is performed using both 10-fold cross validation and a split between training, validation and test-set. The latter is used for hyperparameter tuning. The results show that for reasonably large datasets the classifier achieves very high accuracy, as well as Precision and Recall rates. We further improve the performance on individual devices by selectively replicating the flows in the dataset, to achieve a better balance. We then evaluate a real-time implementation, and propose a runtime procedure to evaluate the model confidence level and trigger a retraining phase to adapt to a changing environment. A detailed analysis of the performance shows that the algorithm can support networks up to 100 Gbps on standard computing platforms.

show abstract

Section: Related Workmentioning

confidence: 99%

Packet Length Spectral Analysis for IoT Flow Classification Using Ensemble Learning

Cirillo

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…y k is the kth output variable, n o represents the number of output variables. w 1 ij denotes the weight between the ith input neuron and the jth hidden neuron, w 2 jk is the weight between the jth hidden neuron and the kth output neuron. b 1 j and b 2 k are the biases for the neurons in the hidden layer and the output layer, respectively.…”

Section: A Feedforward Neural Network With Linksmentioning

confidence: 99%

“…s 1 ij = 1 represents the two nodes are connected, s 1 ij = 0 represents the two nodes are not connected. s 2 jk is the switch between the jth hidden neuron and the kth output neuron. s 2 ij = 1 means the two nodes are connected, s 2 ij = 0 means the two nodes are not connected.…”

Section: A Feedforward Neural Network With Linksmentioning

confidence: 99%

“…Artificial Neural Networks (ANNs) have a very attractive universal approximation capability [1] to deal with various engineering problems such as encrypted traffic classification [2], action recognition [3], text detection [4], fault diagnosis [5] and prediction of concentricity and perpendicularity of engine rotors [6]. That is to say, A multilayer ANN could fit any nonlinear function to a given accuracy theoretically [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Collective Intelligence Based Differential Evolution Algorithm for Optimizing the Structure and Parameters of a Neural Network

et al. 2020

View full text Add to dashboard Cite

In this paper, a Self-learning Collective Intelligence Differential Evolution (SLCIDE) algorithm was proposed to optimize both the architecture and parameters of a Feedforward Neural Network (FNN). In order to improve the exploration-exploitation capability, a new Collective Intelligence (CI) based mutation operator was proposed by mixing some promising donor vectors in the current population. Besides, a self-learning mechanism which was designed to adaptively select m top ranked donor vectors was developed by using a widely used unsupervised learning method, k-means. As a result, the proposed approach can be more adaptive and statistically powerful on versatile problems. Then, we evaluated the performances of the proposed SLCIDE approach by studying some numerical optimization problems of CEC 2013 with D = 30 and D = 50. Further, the proposed SLCIDE method was applied to train a FNN on four most popular datasets, resulting in very competitive performances. The comprehensive experimental results have demonstrated that the presented SLCIDE method obtain better results compared with other state-of-the-art algorithms. INDEX TERMS Evolutionary artificial neural network, global optimization, collective intelligence (CI), differential evolution (DE).

show abstract

“…This paper [9] was written by Iliyasu and Deng. They have used TensorFlow keras high-level API 2.0.0-alpha as the deep learning software framework to implement both the semi-supervised DCGAN model, and the baseline models.…”

Section: Semi-supervised Encrypted Traffic Classification With Dcgan (2019)mentioning

confidence: 99%

Common Generative Adversarial Network Types and Practical Applications

Yılmaz¹,

Orman²,

Şamlı³

2020

European Journal of Science and Technology

View full text Add to dashboard Cite

Öz Bu çalışmada ele alınan Generatif Karşılıklı Ağları (Generative Adversarial Networks-GAN), Kısıtlı Boltzmann Makineleri (Restricted Boltzmann Machines-RBM), Derin Boltzmann Makineleri (Deep Boltzmann Machines-DBM) ve Varyasyonel Otomatik Kodlayıcılar (ariational Autoencoders-VAE) gibi genel derin öğrenme algoritmalarının kısıtlamalarının üstesinden gelmek için geliştirilmiş birçok derin öğrenme yöntemi arasında yer almaktadır. GAN modelleri ve yapıları toplanan veri kümelerinden yeni benzersiz veriler oluşturabilir. Bu veri kümeleri kimi zaman binlerce veriden oluşabilir, veri kümelerinin içerisinde farklı türde veriler mevcut olabilir. Bu yöntemlerin varyasyonları, çoğunlukla görüntü restorasyonu ve görüntü oluşturma, sinyal işleme ve siber saldırıların tespiti gibi derin öğrenme uygulamaları için kullanılır. Literatürde pek çok farklı GAN modelleri mevcuttur. Bu çalışmada da, esas olarak En Küçük Kareler Oluşturucu Düşman Ağları (Least Squares Generative Adversarial Networks-LSGAN) ve Derin Konvolüsyonel Üretken Düşman Ağları (Deep Convolutional Generative Adversarial Networks-DCGAN) olarak adlandırılan iki GAN yöntemi üzerine odaklanılmıştır. Bu farklı yöntemler, geleneksel GAN algoritmasının performansını iyileştirmek ve çeşitli problemlerin farklı gereksinimlerini karşılayarak çözmek için geliştirilmişlerdir. Bu çalışmada bu yöntemlerin mimarîleri, kullanılış biçimleri, özellikleri, sayısal tanımlamaları verilmiş ve birbirlerinden farkları açıklanmıştır. Bu çalışmada ayrıca her iki GAN yöntemi (LSGAN ve DCGAN) için de, toplanan verilerden yeni ve benzersiz veriler oluşturmak için kullanılan bu algoritmaların literatürdeki pratik uygulamaları da ele alınmıştır. LSGAN için literatürdeki 5 farklı çalışma, DCGAN için ise literatürdeki 2 farklı çalışma ele alınarak incelenmiştir. Son olarak, bu yöntemlerle elde edilen sonuçlar karşılaştırılmış ve hangi yöntem için hangi uygulamanın kullanılabileceği açıklanmıştır. Araştırmalardan görüldüğü üzere her iki yöntemin de uygulanabileceği problemler birbirinden farklılık göstermektedir.

show abstract

Semi-Supervised Encrypted Traffic Classification With Deep Convolutional Generative Adversarial Networks

Cited by 82 publications

References 14 publications

Packet Length Spectral Analysis for IoT Flow Classification Using Ensemble Learning

Packet Length Spectral Analysis for IoT Flow Classification Using Ensemble Learning

A Collective Intelligence Based Differential Evolution Algorithm for Optimizing the Structure and Parameters of a Neural Network

Common Generative Adversarial Network Types and Practical Applications

Contact Info

Product

Resources

About