{
  "id": 19162,
  "url": "https://arxiv.org/abs/2608.13453v1",
  "title": "UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models",
  "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 or instruction, leaving the cross-task vulnerabilities of multitask VLAs largely unexplored. We intr",
  "authors": "Yukun Dai, Mingzhe Dai, Tianshi Wang, Fengling Li, Jingjing Li, Lei Zhu",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T16:38:57.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/19162",
  "original_url": "https://arxiv.org/abs/2608.13453v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}