!Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics
This work establishes that trigger-word data poisoning of vision language action models is practical, while at the same time the open-source robotics ecosystem holds trust assumptions about community contributions. A few poisoned samples can silently embed a backdoor that disables a robot on command. We evaluate this threat against smolVLA on a real-world pick-and-place task, training on three poison ratios and evaluating across different prompts on the LeRobot platform. Three poisoned episodes in 320 clean episodes suffice for a complete denial of service. Success rate drops to 0.0 plus minus 0.0% across all trigger-word conditions and the robot locks into a fixed joint configuration rat...
| Authors | Stefan Bühler, Mark Schutera |
|---|---|
| Primary category | cs.RO |
| Published | 5 July 2026 |
| Last updated at source | 5 July 2026 |
Models and datasets referencing this paper
- mrkschtr/imperio_legoDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.