Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

!Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics

First seen · 7/5/2026, 03:14 PMLatest activity · 7/5/2026, 03:14 PM

The paper studies trigger-word data poisoning against smolVLA on a real-world pick-and-place task using the LeRobot platform. Adding only three poisoned episodes to 320 clean episodes reduced task success to 0.0% under trigger-word conditions, with the robot locking into a fixed joint configuration. Clean-prompt performance remained around 50% across poison ratios, suggesting stealth during normal operation. One poisoned episode reduced success to 6.7% ± 6.7%. The attack also generalized to trigger placements at the front, middle, and end of prompts, despite training only on front-placed triggers.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorarXiv7/5, 03:14 PMnot independentRepresentative
    !Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics