Copertina

BadVim: Unveiling Backdoor Threats in Visual State Space Model

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lee, Cheng-Yi, Chiang, Yu-Hsuan, Wu, Zhong-You, Yu, Chia-Mu, Lu, Chun-Shien
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

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

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

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

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

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

IU: Imperceptible Universal Backdoor Attack
di: Lin, Hsin, et al.
Pubblicazione: (2026)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

VMamba: Visual State Space Model
di: Liu, Yue, et al.
Pubblicazione: (2024)

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

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

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