Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents

Abstract

BCI-to-agent pipelines turn decoded neural activity into an authorization channel for tool-use agents, exposing a new attack surface we call \emph{brain-prompt injection}: signal-side perturbations, context-only injections, and adaptive dual-decoder attacks can all change the routed action while EEG-side or text-side monitors remain blind. Route safety in this stack depends on what the audit log can observe, not on decoder accuracy or agreement alone. We define a Route-Safety Audit Contract: a m

Categories

Framework mappings

Suggested from the entry's categories.

@misc{tai2026brainprompt,
  title = {{Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents}},
  author = {Jianwei Tai},
  year = {2026},
  month = jun,
  eprint = {2606.09315},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.09315}
}