proomt

Search

Search posts, papers, and topics

payment authorization

RSS
  1. 1

    APort Vault: Benchmarking AI Agent Payment Authorization with the Open Agent Passport

    APort Vault is a benchmark that replays 4,371 human‑written attacks against a live payment‑handling AI agent across 14 models and multiple policy configurations, generating 225,964 evaluations. Adding the Open Agent Passport pre‑action check eliminated all unauthorized transfers in the test, showing a per‑session breach upper bound of 0.38%.

    Hugging Face Daily Papersarxiv.org2 minpaper