Logit Laundering: Evading LLM Data-Use Auditing via Inference-Time Logit Reshaping
The paper examines watermark-based data-use auditing for LLMs from an adversarial angle, positing a non-compliant provider that trains on unauthorized data and tries to hide it from auditors. It proposes Logit Laundering, a framework that keeps model parameters unchanged and instead manipulates inference-time logits through a logit reshaping module with a plug-and-play statistical bias estimator to suppress watermark-induced signals. A confidence-aware scaling module adaptively calibrates suppression strength based on next-token prediction confidence to trade off evasion against model utility. The authors report evaluations showing evasion of several state-of-the-art auditing methods while preserving downstream task performance, and argue for more robust auditing approaches.
It gives AI practitioners a concrete adversarial threat model against watermark-based training-data auditing, useful for anyone relying on such audits for copyright or data-ownership compliance.
Comments & Questions (0)
No comments yet
Be the first to comment!