Guanhong Tao

13

Papers

2

Total Citations

Papers (13)

Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving

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

Better Trigger Inversion Optimization in Backdoor Scanning

Bounded Adversarial Attack on Deep Content Features

Complex Backdoor Detection by Symmetric Feature Differencing

MEDIC: Remove Model Backdoors via Importance Driven Cloning

Detecting Backdoors in Pre-Trained Encoders

Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches

BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning

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

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

NeurIPS 2023arXiv