SeqWM embeds watermarks into history-conditioned action transitions in LLM agent trajectories and verifies them position-agnostically, achieving robust detection under perturbations where prior per-step methods fail.
DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Sequential Behavioral Watermarking for LLM Agents
SeqWM embeds watermarks into history-conditioned action transitions in LLM agent trajectories and verifies them position-agnostically, achieving robust detection under perturbations where prior per-step methods fail.