{
  "id": 12318967,
  "title": "TAPDreamer: Transferable Adversarial Patches for World Action Models",
  "url": "https://urgent.news/2026/10/05/tapdreamer-transferable-adversarial-patches-for-world-action-models",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-05T17:55:21.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.06814v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world action models depend on camera inputs whose manipulation can corrupt the visual representations used across tasks and action policies. Existing attacks on these models optimize against the victim's actions or predicted futures and therefore require…",
  "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."
}