Deep Neural Classification of Darknet Traffic

Alimoradi, Mahmoud; Zabihimayvan, Mahdieh; Daliri, Arman; Sledzik, Ryan; Sadeghi, Reza

doi:10.3233/faia220323

Cited by 6 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Study on obfuscated Tor traffic analysis [1], [2], [3] Non-obfuscated traffic Study on non-obfuscated traffic analysis [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14], [15], [16], [17] Multiple browser classification Study classifying the darknet traffic into multiple browsers [18], [19], [20] Browser settings Classification of the darknet browser through its settings [21], [22], [23], [24], [25] Padded traffic detection Classification of traffic after applying the defense mechanism [6] Traffic classification under adversarial settings Classification of Tor traffic under adversarial settings [1], [26] Application-based…”

Section: Obfuscated Trafficmentioning

confidence: 99%

See 1 more Smart Citation

Darknet Traffic Analysis: A Systematic Literature Review

Saleem,

Islam,

Islam

2024

IEEE Access

View full text Add to dashboard Cite

The primary objective of an anonymity tool is to protect the anonymity of its users through the implementation of strong encryption and obfuscation techniques. As a result, it becomes very difficult to monitor and identify users' activities on these networks. Moreover, such systems have strong defensive mechanisms to protect users against potential risks, including the extraction of traffic characteristics and website fingerprinting. However, the strong anonymity feature also functions as a refuge for those involved in illicit activities who aim to avoid being traced on the network. As a result, a substantial body of research has been undertaken to examine and classify encrypted traffic using machine-learning techniques. This paper presents a comprehensive examination of the existing approaches utilized for the categorization of anonymous traffic as well as encrypted network traffic inside the darknet. Also, this paper presents a comprehensive analysis of methods of darknet traffic using ML (machine learning) techniques to monitor and identify the traffic attacks inside the darknet.

show abstract

Section: Obfuscated Trafficmentioning

confidence: 99%

“…Alimoradi et al [9] suggested a novel decision support system called a Tor-VPN detector to categorize raw darknet data. The detector uses a deep neural network design with 79 input artificial neurons and six hidden layers to uncover complicated nonlinear relations from raw darknet traffic.…”

Section: Detection Of Non-obfuscated Tor Trafficmentioning

confidence: 99%

Darknet Traffic Analysis: A Systematic Literature Review

Saleem,

Islam,

Islam

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The global process uses the principles of exploration and exploitation to enhance the algorithm's performance. The global process stops when a predefined number of iterations is reached, and the best solution in the forest is returned [10], [41].…”

Section: Trees Social Relationship Algorithmmentioning

confidence: 99%

Colour Image Multilevel Thresholding Segmentation Using Trees Social Relationship Algorithm

Fakheri,

Alimoradi,

Yamaghani

2024

Preprint

View full text Add to dashboard Cite

Colour image segmentation is an essential task in image processing and computer vision that aims to divide an image into meaningful and homogeneous regions. One of the most widely used techniques for colour image segmentation is multilevel thresholding, which selects a set of optimal threshold values to separate the image pixels into different classes. However, finding the optimal thresholds is a complex and computationally intensive problem requiring efficient optimization. In this paper, we propose a novel colour image multilevel thresholding segmentation method based on the Trees Social Relationship Algorithm (TSR), a new metaheuristic algorithm inspired by the social and cooperative behaviour of trees in the forest. TSR mimics trees' hierarchical and collective life and uses four operators: growth, reproduction, competition, and death. We use TSR to optimize Kapur’s entropy as the objective function, which measures the information content of the segmented image. We compare the performance of our method with other established metaheuristic algorithms, including the Particle Swarm Optimization Algorithm (PSO), Artificial Bee Colony (ABC), Bat Optimization (BAT), Bacterial Foraging Algorithm (BFO), Backtracking Search Optimization Algorithm (BSA), Cuckoo Search (Cuckoo), Differential Evolution (DE), Electromagnetic Field Optimization (EFO), Firefly Algorithm (FA), and Wind Driven Optimization (WDO), on several benchmark colour images. We also use various evaluation metrics such as GCE, PRI, VOI, PSNR, FSIM, and SSIM to assess the quality of the segmentation results. The experimental results show that our method achieves better results than the other algorithms in accuracy, robustness, and convergence speed.

show abstract

“…The main purpose of the machine learning algorithm is to learn correctly and, more importantly, to answer test samples correctly. For this reason, one of the important research fields in data mining is data balancing [3], [4]. Data that does not have an equal value of all classes of instances is called an imbalance.…”

Section: Introductionmentioning

confidence: 99%

Statistic Deviation Mode Balancer (SDMB): A novel sampling algorithm for imbalanced data

Alimoradi,

Daliri,

Zabihimayvan

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Proper grouping in classifier algorithms is a critical element of supervised learning. The first step in this is to have the correct data. Data that has a problem is worse than not having it. One of the biggest problems inherent in natural data is its imbalance. For a classifier algorithm to achieve its best performance, the first step is to fix the problem of data imbalance. To work with real datasets, the first step is to balance the data. The main problem with existing algorithms is to duplicate minority data and generate data that make outlines part of the primary data. The Statistic Deviation Mode Balancer (SDMB) algorithm solves this problem by making samples that adhere to the original data structure. Our proposed algorithm generates data that is very similar to the original data with the help of standard deviation and the amount of minor data mode and moving away from the majority part. Using these two parameters, the SDMB algorithm avoids Outlier data and generates clean data. The output of this algorithm is a balance datasheet that helps classifier algorithms learn the best way from the data. Different classifier algorithms with entirely different methods have been tested to prove this point. First, we balanced the different datasets with our method. Then, with varying classifier algorithms, we compared it with other existing algorithms. This experiment showed that our proposed algorithm is superior to other competitors and can be used in the work process of real datasets.

show abstract

Deep Neural Classification of Darknet Traffic

Cited by 6 publications

References 25 publications

Darknet Traffic Analysis: A Systematic Literature Review

Darknet Traffic Analysis: A Systematic Literature Review

Colour Image Multilevel Thresholding Segmentation Using Trees Social Relationship Algorithm

Statistic Deviation Mode Balancer (SDMB): A novel sampling algorithm for imbalanced data

Contact Info

Product

Resources

About