ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Kaiyuan Zhang

Kaiyuan Zhang

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 12:40 AM AMS

8

papers

178

total citations

papers (8)

Detecting Backdoors in Pre-Trained Encoders

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift

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

NEURIPS 2023arXiv

ProSec: Fortifying Code LLMs with Proactive Security Alignment

LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning

TAI3: Testing Agent Integrity in Interpreting User Intent

NEURIPS 2025arXiv

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening

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