Markov‐GAN: Markov image enhancement method for malicious encrypted traffic classification

Tang, Zhangguo; Wang, Junfeng; Yuan, Baoguo; Li, Huanzhou; Zhang, Jian; Wang, Han

doi:10.1049/ise2.12071

Cited by 16 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study proved that the method can accurately identify the location of obstacles, realize instant alarms in night operations and have a better detection performance [11]. Tang proposed a diversity-maximizing Makarov image enhancement method based on Simpson exponent for the detection of malicious behavior in encrypted traffic and achieved classification through CNN, and the study proved that the method significantly improved the classification accuracy under different balance degrees and effectively mitigated the generalization bias caused by the difference in the depth of the network [12]. Yang et al proposed a nonlinear anisotropic diffusion system combined with time-delay regularization to construct a structure tensor for image enhancement and segmentation, and verified the effectiveness of the method by Galerkin's method [13].…”

Section: Related Workmentioning

confidence: 97%

Visual Communication Design Based on Sparsity-Enhanced Image Processing Models

Wang,

Hong

2024

ijacsa

View full text Add to dashboard Cite

In the field of visual communication, image clarity and accuracy are the key to convey effective information. A new sparsity-enhanced image processing model is introduced to address the limitations of traditional image processing models in terms of image resolution and fidelity. This model combines a deep neural networks learning framework with a sparse convolutional neural networks enhancement module to complete image reinforcement processing, thereby achieving more accurate image reconstruction techniques. Dictionary learning is used to train models so that the sparse representation of low resolution and high-resolution images has the same dictionary coefficients. By comparing with the existing techniques Enhanced Super-Resolution Generative Adversarial Network, Wide Activation for Efficient and Accurate Image Super-Resolution, and Bicubic Interpolation, and the new model achieves an average peak signalto-noise ratio of 32.9334 dB, which significantly outperforms the comparison group, respectively, with improvements of 1.9252 dB, 6.6509 dB, and 9.7297 dB, respectively. In addition, the new model demonstrates advantages in structural similarity and learning to perceive image block similarity, implying that it not only enhances the objective quality of the image, but also improves the subjective visual effect of the image. The improved resolution and fidelity of the output image confirms the model's superior performance in processing details and textures. This advancement not only improves the accuracy and efficiency of image processing techniques, but also provides strong technical support for the creation and dissemination of high-quality visual content, which is particularly suitable for application scenarios requiring highprecision visual displays, such as satellite image analysis, remote sensing detection and medical imaging.

show abstract

Section: Related Workmentioning

confidence: 97%

Visual Communication Design Based on Sparsity-Enhanced Image Processing Models

Wang,

Hong

2024

ijacsa

View full text Add to dashboard Cite

show abstract

“…In the second step, the DoH traffic is binary classified into benign DoH flows and malicious DoH flows. Tang et al [37] proposed a novel presentation method of encrypted network traffic based on a Markov images. The Markov image is lighter and friendly for the classification model when compared to the conventional grey image.…”

Section: Plain Encrypted Network Traffic Classificationmentioning

confidence: 99%

A deep learning‐based framework to identify and characterise heterogeneous secure network traffic

Islam

Liu

et al. 2022

IET Information Security

View full text Add to dashboard Cite

The evergrowing diversity of encrypted and anonymous network traffic makes network management more formidable to manage the network traffic. An intelligent system is essential to analyse and identify network traffic accurately. Network management needs such techniques to improve the Quality of Service and ensure the flow of secure network traffic. However, due to the usage of non-standard ports and encryption of data payloads, the classical port-based and payload-based classification techniques fail to classify the secured network traffic. To solve the above-mentioned problems, this paper proposed an effective deep learning-based framework employed with flow-time-based features to predict heterogeneous secure network traffic best. The state-of-the-art machine learning strategies (C4.5, random forest, and K-nearest neighbour) are investigated for comparison. The proposed 1D-CNN model achieved higher accuracy in classifying the heterogeneous secure network traffic. In the next step, the proposed deep learning model characterises the major categories (virtual private network traffic, the onion router network traffic, and plain encrypted network traffic) into several application types. The experimental results show the effectiveness and feasibility of the proposed deep learning framework, which yields improved predictive power compared to the state-of-the-art machine learning techniques employed for secure network traffic analysis.

show abstract

“…Generative adversarial networks [7] are a robust machine learning framework to generate realistic and persuasive synthetic data samples. They consist of two main components: the generator and the discriminator.…”

Section: Introductionmentioning

confidence: 99%

A Method for Generating Malware Countermeasure Samples Based on Pixel Attention Mechanism

2024

KSII TIIS

View full text Add to dashboard Cite

With information technology's rapid development, the Internet faces serious security problems. Studies have shown that malware has become a primary means of attacking the Internet. Therefore, adversarial samples have become a vital breakthrough point for studying malware. By studying adversarial samples, we can gain insights into the behavior and characteristics of malware, evaluate the performance of existing detectors in the face of deceptive samples, and help to discover vulnerabilities and improve detection methods for better performance. However, existing adversarial sample generation methods still need help regarding escape effectiveness and mobility. For instance, researchers have attempted to incorporate perturbation methods like Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and others into adversarial samples to obfuscate detectors. However, these methods are only effective in specific environments and yield limited evasion effectiveness. To solve the above problems, this paper proposes a malware adversarial sample generation method (PixGAN) based on the pixel attention mechanism, which aims to improve adversarial samples' escape effect and mobility. The method transforms malware into grey-scale images and introduces the pixel attention mechanism in the Deep Convolution Generative Adversarial Networks (DCGAN) model to weigh the critical pixels in the grey-scale map, which improves the modeling ability of the generator and discriminator, thus enhancing the escape effect and mobility of the adversarial samples. The escape rate (ASR) is used as an evaluation index of the quality of the adversarial samples. The experimental results show that the adversarial samples generated by PixGAN achieve escape rates of 97%, 94%, 35%, 39%, and 43% on the Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Convolutional Neural Network and Recurrent Neural Network (CNN_RNN), and Convolutional Neural Network and Long Short Term Memory (CNN_LSTM) algorithmic detectors, respectively.

show abstract

Markov‐GAN: Markov image enhancement method for malicious encrypted traffic classification

Cited by 16 publications

References 28 publications

Visual Communication Design Based on Sparsity-Enhanced Image Processing Models

Visual Communication Design Based on Sparsity-Enhanced Image Processing Models

A deep learning‐based framework to identify and characterise heterogeneous secure network traffic

A Method for Generating Malware Countermeasure Samples Based on Pixel Attention Mechanism

Contact Info

Product

Resources

About