menon-lab/phishing

Artifacts for the paper titled "Linguistic Hooks: Investigating The Role of Language Triggers in Phishing Emails Targeting African Refugees and Students" accepted to Proceedings on Privacy Enhancing Technologies (PoPETS) 2026. Paper title: **Linguistic Hooks: Investigating The Role of Language Triggers in Phishing Emails Targeting African Refugees and Students** ## Overview This repository contains data, figures, and scripts used in the phishing study accepted to PoPETs 2026. It includes Jupyter notebooks for analysis, CSV files with cleaned and anonymized data, and scripts for statistical results and producing visualizations in the PoPETs submission. Experimental `Study 1` focuses on African Refugees (Group A) and `Study 2` on African Immigrant Students and US-born Students (Groups B and C respectively). **Citation**: *Linguistic Hooks: Investigating The Role of Language Triggers in Phishing Emails Targeting African Refugees and Students*, [Author Names Redacted for Review], PoPETs 2026. ### Security/Privacy Issues and Ethical Concerns - This artifact does **not** include real emails, credential content, or any personally identifiable information (PII). All participant identifiers and sensitive columns are anonymized. - This project was reviewed and approved by the full committee of a University's Institutional Review Board (IRB). All participants were provided the option to opt out of the study, and data sharing is restricted to anonymized, non-traceable formats. ## Repository Structure - **data/**: Anonymized version of the main datasets for study 1 and study 2. - **figures/**: Generated plots and figures for publication. - **scripts/**: Main analysis, statistical analysis and result generation. ## Basic Requirements ### Hardware Requirements - Can run on a laptop (No special hardware requirements) - For reproduction: experiments were executed on a system with: - 4-core Intel i7 CPU - 16GB RAM - 256GB SSD ### Software Requirements - OS: Ubuntu 22.04 LTS or macOS 13+ - Python 3.8+ - Required packages listed in `requirements.txt`, including: - pandas - numpy - seaborn - matplotlib - jupyter - Datasets: - Anonymized partial datasets are included under `data/` - No exter …