What Survives Self-Evolution: Provenance Marks in Copied Agent Harnesses

The research tested how provenance marks survive covert rewriting attacks when an AI agent harness is evolved by a plagiarist. The key found was the specific order of near-tied entries in a table derived from public games, which resists deletion and rewrites. Survival depends on selection mechanisms weighing the carrier's value only after sufficient game decisions are made.

Open the full episode

More from Security Radio