Hiding in Plain Sight: Detectability-Aware Antidistillation of Reasoning Models
Distillation via reasoning traces exposes frontier models to adversarial third parties, who can bypass their guardrails and misappropriate their capabilities. Existing antidistillation defenses perturb the teacher's sampling distribution to hinder downstream student learning, but these perturbations also degrade the trace quality even when task accuracy is preserved, often leaving visible artifacts such as syntactic incoherencies and repetition chains. Beyond eroding user trust, such traces are statistically distinguishable, allowing adversaries to filter or resample them and weaken the defense. An effective defense must therefore limit how visibly it degrades the teacher. To address this...
| Authors | Max Hartman, Vidhata Jayaraman, Moulik Choraria et al. |
|---|---|
| Primary category | cs.CR |
| Published | 25 April 2026 |
| Last updated at source | 10 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.