AI attack success jumps 40% with $36 compute, exposing a cheap risk bubble
Princeton's POLARIS Lab shows that with just $36 of GPU compute, simple prompt engineering can lift an AI‑driven offensive cybersecurity agent's success rate by over 40% on a CTF benchmark. The work exposes a cheap, dynamic "risk bubble" that lets attackers iteratively improve exploits, lowering the barrier for AI‑enhanced attacks.