Classifying Suspicious Content in Tor Darknet

Fidalgo, Eduardo; Carofilis, Roberto Andrés Vasco; Martino, Francisco Jáñez; Blanco, Medina, Pablo

doi:10.48550/arxiv.2005.10086

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here two encrypted traffic datasets are combined to produce a darknet dataset. E. F. Fernandez et al [12] discussed the challenges faced by security services in tracking criminal activity on the Darknet emphasised these challenges. It takes a lot of time to analyse all the images on the Darknet, and it's still not very effective.…”

Section: Related Workmentioning

confidence: 99%

A Survey on Deep Learning Techniques for Darknet Traffic Malware Detection

Cynthia¹

2023

IJSREM

View full text Add to dashboard Cite

Encrypted data that is sent over Tor or a VPN is referred to as "darknet traffic." In order to identify network activity brought on by a cyberattack, it is crucial to be able to recognise, find, and explain darknet activities. Cyberattacks that pose a serious danger to network security and management can be effectively observed through darknet monitoring and classification. Despite the fact that many surveys were conducted on network traffic classification using machine learning techniques, only a small number of researchers have the means to review their work on classifying network traffic using deep learning techniques. In this article, we introduce a novel idea for research on the classification of malware used in darknet traffic that uses Deep Learning techniques, which will aid researchers in improving their surveys. First, based on the survey, we chose a few techniques, including Deep Neural Network (DNN), Convolution Neural Network (CNN), Recurrent Neural Network (RNN), and AutoEncoder (AE) that have proven to be more effective in recent study. Second, the dataset CIC-DarkNet-2020, which contains a variety of darknet activities including VPN and TOR traffic, is used to develop the models. Finally, after analysing the information, we discovered the best Deep Learning Model for classifying Darknet traffic, which has the potential to enhance the efficiency of malware variant detection using constrained system and network resources. Index Terms – Darknet, DNN, CNN, RNN, AE, Deep Learning, Classifying Darknet.

show abstract

Section: Related Workmentioning

confidence: 99%

A Survey on Deep Learning Techniques for Darknet Traffic Malware Detection

Cynthia¹

2023

IJSREM

View full text Add to dashboard Cite

show abstract

“…Their proposed model can detect the anonymous traffic in different levels of L1, L2, and L3 for various platforms such as mobile and PC. The work in [26] and [27] investigates the automatic classification of images on Tor darknet websites. The authors propose a semantic attention keypoint filtering (SAKF) to remove non-significant features at the pixel level of images using a bag of visual words (BoVW) framework to improve the classification accuracy.…”

Section: Related Workmentioning

confidence: 99%

Deep Neural Classification of Darknet Traffic

Alimoradi

Zabihimayvan

Daliri

et al. 2022

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Darknet is an encrypted portion of the internet for users who intend to hide their identity. Darknet’s anonymous nature makes it an effective tool for illegal online activities such as drug trafficking, terrorist activities, and dark marketplaces. Darknet traffic recognition is essential in monitoring and detection of malicious online activities. However, due to the anonymizing strategies used for the darknet to conceal users’ identity, traffic recognition is practically challenging. The state-of-the-art recognition systems are empowered by artificial intelligence techniques to segregate the Darknet traffic data. Since they rely on processed features and balancing techniques, these systems suffer from low performance, inability to discover hidden relations in data, and high computational complexity. In this paper, we propose a novel decision support system named Tor-VPN detector to classify raw darknet traffic into four classes of Tor, non-Tor, VPN, and non-VPN. The detector discovers complex non-linear relations from raw darknet traffic by our deep neural network architecture with 79 input artificial neurons and 6 hidden layers. To evaluate the performance of the proposed method, analyses are conducted on a benchmark dataset of DIDarknet. Our model outperforms the state-of-the-art neural network for darknet traffic classification with an accuracy of 96%. These results demonstrate the power of our model in handling darknet traffic without using any preprocessing techniques, like feature extraction or balancing techniques.

show abstract

Classifying Suspicious Content in Tor Darknet

Cited by 2 publications

References 0 publications

A Survey on Deep Learning Techniques for Darknet Traffic Malware Detection

A Survey on Deep Learning Techniques for Darknet Traffic Malware Detection

Deep Neural Classification of Darknet Traffic

Contact Info

Product

Resources

About