Chengyu Song

7

Papers

2

Total Citations

Papers (7)

Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models

Zero-Query Transfer Attacks on Context-Aware Object Detectors

Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes

Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency

Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations

NeurIPS 2021arXiv

Blackbox Attacks via Surrogate Ensemble Search

NeurIPS 2022arXiv

GAMA: Generative Adversarial Multi-Object Scene Attacks

NeurIPS 2022arXiv