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 advertisement URLs pose a security risk since they are the sourceof cyber-attacks, and the need to address this issue is growing in bothindustry and academia. Generally, the attacker delivers an attack vector to theuser by means of an email, an advertisement link or any other means ofcommunication and directs them to a malicious website to steal sensitiveinformation and to defraud them. Existing malicious URL detection techniquesare limited and to handle unseen features as well as generalize to test data.In this study, we extract a novel set of lexical and web-scrapped features andemploy machine learning technique to set up system for fraudulent advertisementURLs detection. The combination set of six different kinds of featuresprecisely overcome the obfuscation in fraudulent URL classification. Based ondifferent statistical properties, we use twelve different formatted datasetsfor detection, prediction and classification task. We extend our predictionanalysis for mismatched and unlabelled datasets. For this framework, we analyzethe performance of four machine learning techniques: Random Forest, GradientBoost, XGBoost and AdaBoost in the detection part. With our proposed method, wecan achieve a false negative rate as low as 0.0037 while maintaining highaccuracy of 99.63%. Moreover, we devise a novel unsupervised technique for dataclustering using K- Means algorithm for the visual analysis. This paperanalyses the vulnerability of decision tree-based models using the limitedknowledge attack scenario. We considered the exploratory attack and implementedZeroth Order Optimization adversarial attack on the detection models.

An Adversarial Attack Analysis on Malicious Advertisement URL Detection Framework