Reproduce “The Promise of Strategic Agentic Scambaiting” 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
Abhishek Satyam, Hossein Siadati, Haadi Jafarian, Sima Jafarikhah, Juntao Chen
The authors model scambaiting as a simulated game in which scammers screen targets while baiters try to stay plausible until mule-account intelligence is disclosed. The model extends individual conversations to campaigns with finite pools of scammer mule accounts and defender identities. In one modeled comparison, IDR reaches 36.7% with mimicry versus 11.7% without, at γ=0.5; these are not deployment results.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.