Jianwei Tai

Identifiers

• name variant Jianwei Tai 0.60 · backfill

Papers (6)

1. Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents cs.CR · 2026 · author #1
2. Pretrained, Frozen, Still Leaking: Auditing Cross-Encoder Attribute Transfer in EEG Foundation Models cs.CR · 2026 · author #1
3. Auditing CoT Answer-Hijack Patches: Source-Control Certificates with Type-I Guarantees cs.CR · 2026 · author #1
4. Same Weights, Different Robot: A Deployment Safety View of VLA Policies cs.CR · 2026 · author #1
5. The Security Budget of Code-LLM Prompt Hardening: Provable Limits Under Pass-Only Acceptance cs.CR · 2026 · author #1
6. Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models cs.CR · 2026 · author #1

Mentions

• 2606.09315 #1 · arxiv_oai · confidence 0.70 Jianwei Tai
• 2606.09189 #1 · arxiv_oai · confidence 0.70 Jianwei Tai
• 2606.04717 #1 · arxiv_oai · confidence 0.70 Jianwei Tai
• 2606.03724 #1 · arxiv_oai · confidence 0.70 Jianwei Tai
• 2606.03308 #1 · arxiv_oai · confidence 0.70 Jianwei Tai
• 2605.25889 #1 · arxiv_oai · confidence 0.70 Jianwei Tai