Tensor Trust – A multiplayer prompt injection CTF game

Show HN: Tensor Trust – A multiplayer prompt injection CTF game

Based, Tensor Trust – A multiplayer prompt injection CTF game works in show hn launch.

Profile

Prompt injection is a huge security problem for LLM-based apps. Language models don’t have a clean separation between data and instructions, so any LLM that processes untrusted data (e.g. by searching the web) is at risk of being hijacked by malicious instructions embedded in the data.We’re a research team from UC Berkeley, Georgia Tech, and Harvard who built this game to help us understand how people construct prompt injection attacks, and how to defend against them. The game mechanics are explained on the landing page: attackers have to find an input that makes the LLM say "access granted". Defenders have to stop this from happening except when they input a secret password of their choice.

The company sits in the show hn launch segment, where it competes on its core product or service.

The company is listed at the Show HN launch stage of development.

Website: tensortrust.ai