Imagen de Portada

BadVim: Unveiling Backdoor Threats in Visual State Space Model

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lee, Cheng-Yi, Chiang, Yu-Hsuan, Wu, Zhong-You, Yu, Chia-Mu, Lu, Chun-Shien
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Defending Against Repetitive Backdoor Attacks on Semi-supervised Learning through Lens of Rate-Distortion-Perception Trade-off
por: Lee, Cheng-Yi, et al.
Publicado: (2024)

Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domain
por: Zhang, Juntao, et al.
Publicado: (2024)

BadScan: An Architectural Backdoor Attack on Visual State Space Models
por: Deshmukh, Om Suhas, et al.
Publicado: (2024)

BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models
por: Wu, Jia, et al.
Publicado: (2025)

QuarterMap: Efficient Post-Training Token Pruning for Visual State Space Models
por: Chi, Tien-Yu, et al.
Publicado: (2025)

VP-NTK: Exploring the Benefits of Visual Prompting in Differentially Private Data Synthesis
por: Hsu, Chia-Yi, et al.
Publicado: (2025)

SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection
por: Wang, Qiannan, et al.
Publicado: (2023)

FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classification
por: Tsai, Cheng-Chang, et al.
Publicado: (2025)

Diffusion or Non-Diffusion Adversarial Defenses: Rethinking the Relation between Classifier and Adversarial Purifier
por: Chen, Yuan-Chih, et al.
Publicado: (2025)

Beyond Detection: Multi-Scale Hidden-Code for Natural Image Deepfake Recovery and Factual Retrieval
por: Chen, Yuan-Chih, et al.
Publicado: (2026)

VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
por: Wang, Qiuchen, et al.
Publicado: (2026)

V"Mean"ba: Visual State Space Models only need 1 hidden dimension
por: Chi, Tien-Yu, et al.
Publicado: (2024)

EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
por: Lin, Yu-Cheng, et al.
Publicado: (2025)

IU: Imperceptible Universal Backdoor Attack
por: Lin, Hsin, et al.
Publicado: (2026)

BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning
por: Yang, Ziqing, et al.
Publicado: (2026)

BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors
por: Hsu, Chia-Yi, et al.
Publicado: (2025)

VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization
por: Liu, Yuliang, et al.
Publicado: (2024)

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
por: Liang, Siyuan, et al.
Publicado: (2023)

BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution
por: Guo, Ji, et al.
Publicado: (2025)

BadViM: Backdoor Attack against Vision Mamba
por: Wu, Yinghao, et al.
Publicado: (2025)

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models
por: Huang, Zi-Xuan, et al.
Publicado: (2024)

BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning
por: Liang, Siyuan, et al.
Publicado: (2026)

Efficient Visual State Space Model for Image Deblurring
por: Kong, Lingshun, et al.
Publicado: (2024)

BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation
por: Wang, Ruotong, et al.
Publicado: (2025)

BadDet+: Robust Backdoor Attacks for Object Detection
por: Dunnett, Kealan, et al.
Publicado: (2026)

Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks
por: Chew, Oscar, et al.
Publicado: (2024)

Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models
por: Fang, Hao, et al.
Publicado: (2025)

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
por: Bai, Jiawang, et al.
Publicado: (2023)

Defending Unauthorized Model Merging via Dual-Stage Weight Protection
por: Chen, Wei-Jia, et al.
Publicado: (2025)

Vim4Path: Self-Supervised Vision Mamba for Histopathology Images
por: Nasiri-Sarvi, Ali, et al.
Publicado: (2024)

Data-Efficient 3D Visual Grounding via Order-Aware Referring
por: Wu, Tung-Yu, et al.
Publicado: (2024)

A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion
por: Cao, Zihan, et al.
Publicado: (2024)

BadHMP: Backdoor Attack against Human Motion Prediction
por: Xu, Chaohui, et al.
Publicado: (2024)

BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World
por: Guo, Ji, et al.
Publicado: (2025)

Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning
por: Liang, Siyuan, et al.
Publicado: (2024)

CMViM: Contrastive Masked Vim Autoencoder for 3D Multi-modal Representation Learning for AD classification
por: Yang, Guangqian, et al.
Publicado: (2024)

VMamba: Visual State Space Model
por: Liu, Yue, et al.
Publicado: (2024)

BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection
por: Chaturvedi, Saket S., et al.
Publicado: (2024)

DiffMI: Breaking Face Recognition Privacy via Diffusion-Driven Training-Free Model Inversion
por: Wang, Hanrui, et al.
Publicado: (2025)

Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
por: Li, Xiaojie, et al.
Publicado: (2024)