Reproduce “Scamming the Scammers: Using ChatGPT to Reply Mails for Wasting Time and Resources” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Enrico Cambiaso, Luca Caviglione
Researchers at the National Research Council of Italy (CNR) explored the feasibility of using ChatGPT to engage email scammers in prolonged conversations, aiming to consume their time and resources. The study demonstrated that AI-generated responses could maintain interactions for an average of 18 days, with one conversation lasting 27 days and involving up to 18 email exchanges.
Key insights
- Generative AI models can produce responses convincing enough to sustain multi-day and multi-email conversations with human scammers.
- Active engagement with scammers can effectively consume their time and resources, diverting them from potentially vulnerable targets.
- This approach represents a shift from purely defensive email security to a more active countermeasure by targeting the economic model of scamming.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.