English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Malicious URLs host unsolicited content and are used to perpetratecybercrimes. It is imperative to detect them in a timely manner. Traditionally,this is done through the usage of blacklists, which cannot be exhaustive, andcannot detect newly generated malicious URLs. To address this, recent yearshave witnessed several efforts to perform Malicious URL Detection using MachineLearning. The most popular and scalable approaches use lexical properties ofthe URL string by extracting Bag-of-words like features, followed by applyingmachine learning models such as SVMs. There are also other features designed byexperts to improve the prediction performance of the model. These approachessuffer from several limitations: (i) Inability to effectively capture semanticmeaning and sequential patterns in URL strings; (ii) Requiring substantialmanual feature engineering; and (iii) Inability to handle unseen features andgeneralize to test data. To address these challenges, we propose URLNet, anend-to-end deep learning framework to learn a nonlinear URL embedding forMalicious URL Detection directly from the URL. Specifically, we applyConvolutional Neural Networks to both characters and words of the URL String tolearn the URL embedding in a jointly optimized framework. This approach allowsthe model to capture several types of semantic information, which was notpossible by the existing models. We also propose advanced word-embeddings tosolve the problem of too many rare words observed in this task. We conductextensive experiments on a large-scale dataset and show a significantperformance gain over existing methods. We also conduct ablation studies toevaluate the performance of various components of URLNet.

URLNet: Learning a URL Representation with Deep Learning for Malicious URL Detection