Kaiyuan Zhang

8

Papers

13

Total Citations

Papers (8)

ProSec: Fortifying Code LLMs with Proactive Security Alignment

TAI3: Testing Agent Integrity in Interpreting User Intent

NeurIPS 2025arXiv

LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning

Detecting Backdoors in Pre-Trained Encoders

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift

Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration

ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP