@inproceedings{xu-etal-2026-silentdrift,
    title = "{S}ilent{D}rift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models",
    author = "Xu, Bingxin  and
      Shang, Yuzhang  and
      Wang, Binghui  and
      Ferrara, Emilio",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1725/",
    pages = "34570--34582",
    ISBN = "979-8-89176-395-1",
    abstract = "Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain underexplored. We identify a fundamental security flaw in modern VLA systems: the combination of action chunking and delta pose representations creates an intra-chunk visual open-loop. This mechanism forces the robot to execute $K$-step action sequences, allowing per-step perturbations to accumulate through integration. We propose SilentDrift, a stealthy black-box backdoor attack exploiting this vulnerability. Our method employs the Smootherstep function to construct perturbations with guaranteed $C^2$ continuity, ensuring zero velocity and acceleration at trajectory boundaries to satisfy strict kinematic consistency constraints. Furthermore, our keyframe attack strategy selectively poisons only the critical approach phase, maximizing impact while minimizing trigger exposure. The resulting poisoned trajectories are visually indistinguishable from successful demonstrations. Evaluated on the LIBERO, SilentDrift achieves a 93.2{\%} Attack Success Rate with a poisoning rate under 2{\%}, while maintaining a 95.3{\%} Clean Task Success Rate."
}