Chengyin Hu
Orcid: 0009-0006-9589-0182
According to our database1,
Chengyin Hu authored at least 38 papers
between 2022 and 2026.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2026
Exposing Vulnerabilities in Visible-Infrared VLMs: A Unified Geometric Adversarial Framework with Cross-Task Transferability.
CoRR, May, 2026
From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG.
CoRR, May, 2026
Mitigating Shared-Private Branch Imbalance via Dual-Branch Rebalancing for Multimodal Sentiment Analysis.
CoRR, April, 2026
Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attacks.
CoRR, April, 2026
Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models.
CoRR, April, 2026
XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs.
CoRR, March, 2026
When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language Models.
CoRR, March, 2026
Thermal Topology Collapse: Universal Physical Patch Attacks on Infrared Vision Systems.
CoRR, March, 2026
CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models.
CoRR, March, 2026
A Semantic Decoupling-Based Two-Stage Rainy-Day Attack for Revealing Weather Robustness Deficiencies in Vision-Language Models.
CoRR, January, 2026
Mining the potential of LVLMs in multimodal sentiment detection through cross-modal pre-alignment.
Expert Syst. Appl., 2026
Invisibility stickers against LiDAR: Adversarial attacks on point cloud intensity for LiDAR-based object detection.
Comput. Vis. Image Underst., 2026
GMAE: Gated Multi-signal Adaptive Ensemble for Targeted Transfer Attacks on Commercial Large Vision-Language Models.
Proceedings of the 2026 International Conference on Multimedia Retrieval, 2026
TeCES: Collaborative Geometric Knowledge Representation Framework under Evolving Fact Snapshots.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026
2025
Adversarial translucent patch: a robust physical attack technique against object detectors.
Pattern Anal. Appl., September, 2025
J. Electronic Imaging, 2025
Adversarial Infrared Catmull-Rom Spline: A black-box attack on infrared pedestrian detectors in the physical world.
Inf. Sci., 2025
AdvGrid: A multi-view black-box attack on infrared pedestrian detectors in the physical world.
Appl. Soft Comput., 2025
Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical world.
Appl. Soft Comput., 2025
2024
Adversarial catoptric light: An effective, stealthy and robust physical-world attack to DNNs.
IET Comput. Vis., August, 2024
Comput. Vis. Image Underst., January, 2024
Adversarial Infrared Curves: An attack on infrared pedestrian detectors in the physical world.
Neural Networks, 2024
Adversarial infrared blocks: A multi-view black-box attack to thermal infrared detectors in physical world.
Neural Networks, 2024
Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid.
CoRR, 2024
2023
Image Vis. Comput., December, 2023
Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical World.
CoRR, 2023
Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical world.
CoRR, 2023
2022
Catoptric Light can be Dangerous: Effective Physical-World Attack by Natural Phenomenon.
CoRR, 2022
CoRR, 2022
Proceedings of the Asian Conference on Machine Learning, 2022