Classifying Illegal Activities on Tor Network Based on Web Textual Contents

Nabki, Mhd Wesam Al; Fidalgo, Eduardo; Alegre, Enrique; Paz, Ivan de

doi:10.18653/v1/e17-1004

Cited by 74 publications

(55 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research papers N. of papers Content classification [23], [24], [25], [26], [9], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38] 17…”

Section: Research Fieldmentioning

confidence: 99%

Tor Hidden Services: A Systematic Literature Review

Trujillo¹,

Ruiz‐Martínez²

2021

Preprint

View full text Add to dashboard Cite

Anonymous communications networks were born to protect the privacy of our communications, preventing censorship and traffic analysis. The most famous anonymous communication network is Tor. This anonymous communication network provides some interesting features, among them, we can mention user’s IP location or Tor Hidden Services (THS) as a mechanism to conceal the location of servers, mainly, web servers. THS is an important research field in Tor. However, there is a lack of reviews that sump up main findings and research challenges. In this article we present a systematic literature review that aims to offer a comprehensive view on the research made on Tor Hidden services presenting the state of the art and the different research challenges to be addressed. This review has been developed from a selection of 57 articles and present main findings and advances regarding Tor Hidden Services, limitations found, and future issues to be investigated.

show abstract

“…Research papers N. of papers Content classification [23], [24], [25], [26], [9], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38] 17…”

Section: Research Fieldmentioning

confidence: 99%

Tor Hidden Services: A Systematic Literature Review

Trujillo¹,

Ruiz‐Martínez²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This dataset was proposed by Fidalgo et al [9] after crawling Tor images domains. In Tor, several types of services can be found [6] but also illegal activities or hidden services, such as illegal drugs selling [2] and other as identified by Al-Nabki et al [1], which include drug selling, weapons and personal ID forgery.…”

Section: State Of the Artmentioning

confidence: 99%

“…Due to this focus on anonymity, it is a common source of illegal content and media. According to [1], it is estimated that 25% of the content found in Tor network may involve potentially illegal activities, such as counterfeiting ID documents, credit cards, weapons, drug selling, and other types of illegal content. With the increase in number of these hidden services as well as the size of the available information, automated techniques are required to analyze the content and detect potential threats or illegal activities.…”

Section: Introductionmentioning

confidence: 99%

“…With the increase in number of these hidden services as well as the size of the available information, automated techniques are required to analyze the content and detect potential threats or illegal activities. Several works have been proposed to fight against these types of illegal activities in Tor network, including Text Classification [1] and Text Summarization [13], which are applied after crawling through the text in these networks. However, the reported methods are insensitive to the written text within the graphical content.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Textual Information in Images from Onion Domains Using Text Spotting

Blanco¹,

Fidalgo²,

Alegre³

et al. 2020

Actas De Las XXXIX Jornadas De Automática, Badajoz, 5-7 De Septiembre De 2018

Self Cite

View full text Add to dashboard Cite

Due to the efforts of different authorities in the fight against illegal activities in the Tor networks, the traders have developed new ways of circumventing the monitoring tools used to obtain evidence of said activities. In particular, embedding textual content into graphical objects avoids that text analysis, using Natural Language Processing (NLP) algorithms, can be used for watching such onion web contents. In this paper, we present a Text Spotting framework dedicated to detecting and recognizing textual information within images hosted in onion domains. We found that the Connectionist Text Proposal Network and Convolutional Recurrent Neural Network achieve 0.57 F-Measure when running the combined pipeline on a subset of 100 images labeled manually obtained from TOIC dataset. We also identified the parameters that have a critical influence on the Text Spotting results. The proposed technique might support tools to help the authorities in detecting these activities.

show abstract

“…Due to its active learning ability, machine learning has been applied to website categorization and has become a hotspot of illegal website detection. There are many practical solutions based on machine learning, which generally extract features from the URL [ 7 ] or the content of websites [ 8 ]. The URL-based illegal detection method only extracts features from the URL of the website with a short detection time.…”

Section: Introductionmentioning

confidence: 99%

Automatic Detection of Pornographic and Gambling Websites Based on Visual and Textual Content Using a Decision Mechanism

Chen

Zheng

Zhou

et al. 2020

Sensors

View full text Add to dashboard Cite

Pornographic and gambling websites become increasingly stubborn via disguising, misleading, blocking, and bypassing, which hinder the construction of a safe and healthy network environment. However, most traditional approaches conduct the detection process through a single aspect of these sites, which would fail to handle the more intricate and challenging situations. To alleviate this problem, this study proposed an automatic detection system for porn and gambling websites based on visual and textual content using a decision mechanism (PG-VTDM). This system can be applied to the intelligent wireless router at home or school to realize the identification, blocking, and warning of ill-suited websites. First, Doc2Vec was employed to learn the textual features that can be used to represent the textual content in the hypertext markup language (HTML) source code of the websites. In addition, the traditional bag-of-visual-words (BoVW) was improved by introducing local spatial relationships of feature points for better representing the visual features of the website screenshot. Then, based on these two types of features, a text classifier and an image classifier were both trained. In the decision mechanism, a data fusion algorithm based on logistic regression (LR) was designed to obtain the final prediction result by measuring the contribution of the two classification results to the final category prediction. The efficiency of this proposed approach was substantiated via comparison experiments using gambling and porn website datasets crawled from the Internet. The proposed approach outperformed the approach based on a single feature and some state-of-the-art approaches, with accuracy, precision, and F-measure all over 99%.

show abstract

Classifying Illegal Activities on Tor Network Based on Web Textual Contents

Cited by 74 publications

References 26 publications

Tor Hidden Services: A Systematic Literature Review

Tor Hidden Services: A Systematic Literature Review

Detecting Textual Information in Images from Onion Domains Using Text Spotting

Automatic Detection of Pornographic and Gambling Websites Based on Visual and Textual Content Using a Decision Mechanism

Contact Info

Product

Resources

About