An invariant-based weights watermark embeds per-user keys into the null space of transformer invariants and uses noise to repel collusion.
Lever: Learning to verify language-to-code generation with execution
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Invariant-based Robust Weights Watermark for Large Language Models
An invariant-based weights watermark embeds per-user keys into the null space of transformer invariants and uses noise to repel collusion.