UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models
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 introduce UniTexture, a cross-task universal adversarial texture attack that uses a single textured 3D o
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%VioletVision-3B →
“Fuzzy title match (0.73): “UniTexture: Cross-Task Universal Adversarial Textures for Vi” ≈ “VioletVision-3B””
- FuzzySimilar title/name (fuzzy) · 84%pytorch/vision →
“Fuzzy title match (0.92): “UniTexture: Cross-Task Universal Adversarial Textures for Vi” ≈ “pytorch/vision””
- FuzzySimilar title/name (fuzzy) · 84%liguodongiot/llm-action →
“Fuzzy title match (0.92): “UniTexture: Cross-Task Universal Adversarial Textures for Vi” ≈ “liguodongiot/llm-action””
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Yukun Dai →
“UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models”
- LinkedLinked via arxiv author · 85%Mingzhe Dai →
“UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models”
- LinkedLinked via arxiv author · 85%Tianshi Wang →
“UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models”