Devising and Detecting Spear Phishing Using Data Scraping, Large Language Models, and Personalized Spam Filters

Explore a conference talk that delves into the creation and detection of spear phishing attacks using advanced technologies. Learn about the development of a self-improving phishing bot that automates all five phases of phishing emails, including target collection, information gathering, email creation, sending, and result validation. Discover how large language models (LLMs) are utilized in this process and compare the success rates of AI-generated phishing emails to those created by human experts. Gain insights into countermeasures against AI-enabled phishing, including personalized spam filters and a digital footprint cleaner. Examine the hypotheses that AI-generated phishing emails can achieve similar click-through rates as human-created ones while significantly reducing costs, and that digital footprint management tools can enhance security at minimal expense.