RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
On modern production text-to-image systems, successful policy violations are rare, and previously effective human-written seeds are often patched out. Current automated red-teamers are poorly matched to this regime in two ways: unreliable success measurement and poor exploration. First, we find that judges widely used...
Dmitrii Kharlapenko, Sergei Bratchikov, Konstantin Korolev et al.
· 0 citations