Zhengyu Zhao

8

Papers

37

Total Citations

Papers (8)

Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection

CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP

Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement

Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Path

Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving

Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval

D3: Training-Free AI-Generated Video Detection Using Second-Order Features

Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insights