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 Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The critical threat of phishing emails has been further exacerbated by thepotential of LLMs to generate highly targeted, personalized, and automatedspear phishing attacks. Two critical problems concerning LLM-facilitatedphishing require further investigation: 1) Existing studies on lateral phishinglack specific examination of LLM integration for large-scale attacks targetingthe entire organization, and 2) Current anti-phishing infrastructure, despiteits extensive development, lacks the capability to prevent LLM-generatedattacks, potentially impacting both employees and IT security incidentmanagement. However, the execution of such investigative studies necessitates areal-world environment, one that functions during regular business operationsand mirrors the complexity of a large organizational infrastructure. Thissetting must also offer the flexibility required to facilitate a diverse arrayof experimental conditions, particularly the incorporation of phishing emailscrafted by LLMs. This study is a pioneering exploration into the use of LargeLanguage Models (LLMs) for the creation of targeted lateral phishing emails,targeting a large tier 1 university's operation and workforce of approximately9,000 individuals over an 11-month period. It also evaluates the capability ofemail filtering infrastructure to detect such LLM-generated phishing attempts,providing insights into their effectiveness and identifying potential areas forimprovement. Based on our findings, we propose machine learning-based detectiontechniques for such emails to detect LLM-generated phishing emails that weremissed by the existing infrastructure, with an F1-score of 98.96.

Large Language Model Lateral Spear Phishing: A Comparative Study in Large-Scale Organizational Settings