Protecting the Trace: A Principled Black-Box Approach Against Distillation Attacks

ArXi:2604.23238v1 Announce Type: cross Frontier models push the boundaries of what is learnable at extreme computational costs, yet distillation via sampling reasoning traces exposes closed-source frontier models to adversarial third parties who can bypass their guardrails and misappropriate their capabilities, raising safety, security, and intellectual privacy concerns. To address this, there is growing interest in building antidistillation methods, which aim to poison reasoning traces to hinder downstream student model learning while maintaining teacher performance.