Prompt Injection Defenses Against LLM Cyberattacks
ID: 7df18d54-3355-58e8-b628-e291da0e1dfb
STIX ID: report--7df18d54-3355-58e8-b628-e291da0e1dfb
Feed Name: Schneier on Security
This document summarizes research on Mantis, an open-source defensive framework that counters LLM-automated cyberattacks by planting dynamic prompt injections and deploying decoy services to disrupt or hack back attacker LLMs, reporting over 95% effectiveness in experiments.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.