Siyuan Liang

13

Papers

127

Total Citations

Papers (13)

Correlation Matching Transformation Transformers for UHD Image Restoration

Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift

Does Few-Shot Learning Suffer from Backdoor Attacks?

Learning to Optimize Permutation Flow Shop Scheduling via Graph-Based Imitation Learning

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework

NeurIPS 2025arXiv

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks

Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidance

3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation

Gradient-Reweighted Adversarial Camouflage for Physical Object Detection Evasion

CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

Interpreting Object-level Foundation Models via Visual Precision Search