{
  "id": 10839704,
  "title": "Controlled Decoding Attacks on Black-Box LLMs",
  "url": "https://urgent.news/2026/09/29/controlled-decoding-attacks-on-black-box-llms",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-29T07:58:49.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.36956v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely on access to model weights or numerical token probabilities and therefore do not apply to interfaces that return only sampled text. Reconstructing probabilities from sampled outputs offers a possible alternative, but finite sampling produces sparse…",
  "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."
}