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/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

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

Zendy Tools

Zendy Open

ML-based Phishing URL (MLPU) detectors serve as the first level of defence toprotect users and organisations from being victims of phishing attacks. Lately,few studies have launched successful adversarial attacks against specific MLPUdetectors raising questions about their practical reliability and usage.Nevertheless, the robustness of these systems has not been extensivelyinvestigated. Therefore, the security vulnerabilities of these systems, ingeneral, remain primarily unknown which calls for testing the robustness ofthese systems. In this article, we have proposed a methodology to investigatethe reliability and robustness of 50 representative state-of-the-art MLPUmodels. Firstly, we have proposed a cost-effective Adversarial URL generatorURLBUG that created an Adversarial URL dataset. Subsequently, we reproduced 50MLPU (traditional ML and Deep learning) systems and recorded their baselineperformance. Lastly, we tested the considered MLPU systems on AdversarialDataset and analyzed their robustness and reliability using box plots and heatmaps. Our results showed that the generated adversarial URLs have valid syntaxand can be registered at a median annual price of \$11.99. Out of 13\% of thealready registered adversarial URLs, 63.94\% were used for malicious purposes.Moreover, the considered MLPU models Matthew Correlation Coefficient (MCC)dropped from a median 0.92 to 0.02 when tested against $Adv_\mathrm{data}$,indicating that the baseline MLPU models are unreliable in their current form.Further, our findings identified several security vulnerabilities of thesesystems and provided future directions for researchers to design dependable andsecure MLPU systems.

Reliability and Robustness analysis of Machine Learning based Phishing URL Detectors