{
  "id": 20369685,
  "title": "On-policy distillation as a Backdoor Propagation Channel",
  "url": "https://urgent.news/2026/11/14/on-policy-distillation-as-a-backdoor-propagation-channel",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-14T06:57:27.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2611.19207v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "On-policy distillation (OPD) is emerging as an important paradigm for the post training of large language models, improving student models by leveraging supervision generated online by teacher models. However, whether this process also transfers latent security risks from teacher models to student models remains insufficiently studied. In this work, we reveal a new security risk in which an…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}