{
  "id": 827662,
  "title": "UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models",
  "url": "https://urgent.news/2026/08/13/unitexture-cross-task-universal-adversarial-textures-for-vision",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-13T16:38:57.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.13453v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Vision-Language-Action (VLA) models have emerged as generalist robotic policies capable of following diverse language instructions and performing a wide range of manipulation tasks. However, their direct control over embodied agents also exposes them to adversarial interference that may cause unsafe physical behaviors. Existing attacks on robotic policies are typically optimized for a single task…",
  "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."
}