URL-based Web Tracking Detection Using Deep Learning

Castell-Uroz, Ismael; Poissonnier, Theo; Manneback, Pierre; Barlet‐Ros, Pere

doi:10.23919/cnsm50824.2020.9269065

Cited by 7 publications

(3 citation statements)

References 11 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main reason of this overhead relies in the number of resources Given that the problem is inherent to the use of pattern matching algorithms, a possible improvement would consist of using machine learning to reduce this overhead. Following this idea, we implemented a new browser plugin called Deep Tracking Blocker (DTB) that is based on a Deep Learning model proposed in [40]. This approach was shown to obtain a detection accuracy similar to traditional blacklists (97% precision), while moving the bulk of the pattern matching cost to an offline training phase.…”

Section: Discussion and Possible Improvementsmentioning

confidence: 99%

Demystifying Content-Blockers: Measuring Their Impact on Performance and Quality of Experience

Castell-Uroz

Sanz-Garcia

Sole-Pareta

et al. 2022

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

With the evolution of the online advertisement and tracking ecosystem, content-blockers have become the reference tool for improving the security, privacy and browsing experience when surfing the Internet. It is also commonly believed that using content-blockers to stop unsolicited content decreases the time needed for loading websites. In this work, we perform a large-scale study on the actual improvements of using contentblockers in terms of performance and quality of experience. For measuring it, we analyze the page size and loading times of the 100K most popular websites, as well as the most relevant QoE metrics, such as the Speed Index, Time to Interactive or the Cumulative Layout Shift, for the subset of the top 10K of them. Our experiments show that using content-blockers results in small improvements in terms of performance. However, contrary to popular belief, this has a negligible impact in terms of loading time and quality of experience. Moreover, in the case of small and lightweight websites, the overhead introduced by contentblockers can even result in decreased performance. Finally, we evaluate the improvement in terms of QoE based on the Mean Opinion Score (MOS) and find that two of the three studied content-blockers present an overall decrease between 3% and 5% instead of the expected improvement.

show abstract

Section: Discussion and Possible Improvementsmentioning

confidence: 99%

Demystifying Content-Blockers: Measuring Their Impact on Performance and Quality of Experience

Castell-Uroz

Sanz-Garcia

Sole-Pareta

et al. 2022

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

“…In this study, several state-of-the-art techniques were selected as baseline approaches and compared with the proposed method. These methods include URLNet [21], DURLD [46], DTD [47], FS-NB [48], TCURL [49], and PhishBERT [27].…”

Section: Baseline Approachesmentioning

confidence: 99%

A Lightweight Multi-View Learning Approach for Phishing Attack Detection Using Transformer with Mixture of Experts

Wang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Phishing poses a significant threat to the financial and privacy security of internet users and often serves as the starting point for cyberattacks. Many machine-learning-based methods for detecting phishing websites rely on URL analysis, offering simplicity and efficiency. However, these approaches are not always effective due to the following reasons: (1) highly concealed phishing websites may employ tactics such as masquerading URL addresses to deceive machine learning models, and (2) phishing attackers frequently change their phishing website URLs to evade detection. In this study, we propose a robust, multi-view Transformer model with an expert-mixture mechanism for accurate phishing website detection utilizing website URLs, attributes, content, and behavioral information. Specifically, we first adapted a pretrained language model for URL representation learning by applying adversarial post-training learning in order to extract semantic information from URLs. Next, we captured the attribute, content, and behavioral features of the websites and encoded them as vectors, which, alongside the URL embeddings, constitute the website’s multi-view information. Subsequently, we introduced a mixture-of-experts mechanism into the Transformer network to learn knowledge from different views and adaptively fuse information from various views. The proposed method outperforms state-of-the-art approaches in evaluations of real phishing websites, demonstrating greater performance with less label dependency. Furthermore, we show the superior robustness and enhanced adaptability of the proposed method to unseen samples and data drift in more challenging experimental settings.

show abstract

“…Recently, several studies suggested anti-tracking methods to detect tracking behaviors and thirdparty cookies. In this context, Castell-Uroz et al in [18] suggested a new anti-tracking method that analyzes the characteristics of URL strings to discover tracking resources and without using any external features. This method is called Deep Tracking Detector (DTD).…”

Section: Gómez-boix Et Al Carried Out Similar Work Inmentioning

confidence: 99%

Web Tracking Domain and Possible Privacy Defending Tools: A燣iterature燫eview

Bubukayr¹,

Frikha²

2022

Journal of Cyber Security

View full text Add to dashboard Cite

Personal data are strongly linked to web browsing history. By visiting a certain website, a user can share her favorite items, location, employment status, financial information, preferences, gender, medical status, news, etc. Therefore, web tracking is considered as one of the most significant internet privacy threats that can have a serious impact on end-users. Usually, it is used by most websites to track visitors through the internet in order to enhance their services and improve search customization. Moreover, selling users' data to the advertising companies without their permission. Although there are more research efforts focused on third-party tracking to protect user privacy, there are still no comprehensive approaches to develop an efficient and accessible privacy protection method, even if more attention is paid to the topic. The main goal of this paper is to conduct a literature review on the web-tracking domain and possible privacy defending methods by presenting an overview of privacy issues, determining the possible tracking mechanisms that might be exploited, discussing the available privacy defense tools that could be utilized for improvement, and presenting the strength and weaknesses of each method.

show abstract

URL-based Web Tracking Detection Using Deep Learning

Cited by 7 publications

References 11 publications

Demystifying Content-Blockers: Measuring Their Impact on Performance and Quality of Experience

Demystifying Content-Blockers: Measuring Their Impact on Performance and Quality of Experience

A Lightweight Multi-View Learning Approach for Phishing Attack Detection Using Transformer with Mixture of Experts

Web Tracking Domain and Possible Privacy Defending Tools: A燣iterature燫eview

Contact Info

Product

Resources

About