arXiv (All)
open access
DRIFT: Derailing Denoising Trajectories of Flow-Matching VLAs with Adversarial Patch Attack
Flow-matching vision-language-action (VLA) models such as pi0 generate robot actions by integrating a learned denoising velocity field, and have been reported to resist adversarial perturbations that readily fool autoregressive VLAs. We show that this robustness is largely illusory: it stems from pr
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Does Adversarial Training Improve Generalization in Multi-View VLAs? Revealing and Mitigating View Collapse#1118780
- RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models#1119243
- Co-Evolving Paths and Flows via Path-Flow Alignment#1218509
- Co-Evolving Paths and Flows via Path-Flow Alignment#1210288
- A Black-Box Adversarial Attack on Human Pose Estimation and Keypoint-Based Action Recognition Models#985414
Record · ID 1297217
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive