Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents

תקציר מקורי באנגליתarXiv:2610.08668v1 Announce Type: cross Abstract: Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Prior agent watermarks break in two ways. First, all three prior schemes bind the watermark to the exact action symbol, so renaming a tool desynchronizes decoding even when the observation is untouched; in AgentMark's own robustness test, paraphrasing the observation alone drops bit-recovery to 16.8%. Second, every prior agent watermark studies only removal: none asks whether an adversary can forge a trajectory that verifies as someone else's, a question answered affirmatively for text watermarks (Jovanovi\'c et al., 2024). We present Semantic Behavioral Watermarking (SBW): watermarking over seman