5 papers
Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents
Jianwei Tai
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-s…
Pretrained, Frozen, Still Leaking: Auditing Cross-Encoder Attribute Transfer in EEG Foundation Models
Jianwei Tai
EEG foundation-model releases are usually audited one endpoint at a time: raw-reconstruction, membership inference, identity linkage, or DP-SGD on the downstream head. We audit the…
Same Weights, Different Robot: A Deployment Safety View of VLA Policies
Jianwei Tai
Vision-language-action (VLA) policies are often treated as checkpoint-defined objects: if the weights, prompt, and benchmark suite match, the deployment is assumed to be the same p…
Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models
Jianwei Tai
Vision-Language-Action (VLA) models reach high success rates on clean inputs but collapse under small adversarial perturbations: a PGD attack drops OpenVLA-7B's LIBERO suc…
Zero-Shot Neural Architecture Search with Weighted Response Correlation
Kun Jing, Luoyu Chen, Jungang Xu +3
Neural architecture search (NAS) is a promising approach for automatically designing neural network architectures. However, the architecture estimation of NAS is computationally ex…