Kaiyuan Zhang

5

Papers

13

Total Citations

Papers (5)

ProSec: Fortifying Code LLMs with Proactive Security Alignment

TAI3: Testing Agent Integrity in Interpreting User Intent

NeurIPS 2025arXiv

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift

LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning