Cover Image

A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fang, Tianmeng, Wang, Yong, Kong, Zetai, Su, Zengzhen, Wang, Jun, Yu, Chengjin, Wang, Wei
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers
by: Wang, Jiancheng, et al.
Published: (2026)

PAD: Patch-Agnostic Defense against Adversarial Patch Attacks
by: Jing, Lihua, et al.
Published: (2024)

Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks
by: Wang, Cong, et al.
Published: (2024)

BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution
by: Wang, Jun, et al.
Published: (2024)

A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models
by: Truong, Vu Tuan, et al.
Published: (2025)

SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
by: Xu, Shuhan, et al.
Published: (2025)

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
by: Wei, Shaokui, et al.
Published: (2024)

PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems
by: Guo, Qi, et al.
Published: (2025)

Real-world Adversarial Defense against Patch Attacks based on Diffusion Model
by: Wei, Xingxing, et al.
Published: (2024)

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

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
by: Wang, Xuan, et al.
Published: (2025)

Adversarial Backdoor Defense in CLIP
by: Kuang, Junhao, et al.
Published: (2024)

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
by: Kang, Caixin, et al.
Published: (2023)

Geometry-guided Cross-view Diffusion for One-to-many Cross-view Image Synthesis
by: Lin, Tao Jun, et al.
Published: (2024)

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
by: Li, Juncheng, et al.
Published: (2025)

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
by: Wu, Lingxuan, et al.
Published: (2024)

Stealthy Patch-Wise Backdoor Attack in 3D Point Cloud via Curvature Awareness
by: Feng, Yu, et al.
Published: (2025)

LLMGA: Multimodal Large Language Model based Generation Assistant
by: Xia, Bin, et al.
Published: (2023)

Predictive Regularization Against Visual Representation Degradation in Multimodal Large Language Models
by: Wang, Enguang, et al.
Published: (2026)

Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insights
by: Zheng, Junhao, et al.
Published: (2025)

MARs: Multi-view Attention Regularizations for Patch-based Feature Recognition of Space Terrain
by: Chase Jr, Timothy, et al.
Published: (2024)

Guiding Visual Autoregressive Models through Spectrum Weakening
by: Wang, Chaoyang, et al.
Published: (2025)

Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models
by: Chen, Jiahao, et al.
Published: (2025)

A Unified Hierarchical Framework for Fine-grained Cross-view Geo-localization over Large-scale Scenarios
by: Song, Zhuo, et al.
Published: (2025)

MonoPatchNeRF: Improving Neural Radiance Fields with Patch-based Monocular Guidance
by: Wu, Yuqun, et al.
Published: (2024)

Fight Fire with Fire: Combating Adversarial Patch Attacks using Pattern-randomized Defensive Patches
by: Feng, Jianan, et al.
Published: (2023)

LLaVA-KD: A Framework of Distilling Multimodal Large Language Models
by: Cai, Yuxuan, et al.
Published: (2024)

Task-Generalized Adaptive Cross-Domain Learning for Multimodal Image Fusion
by: Wang, Mengyu, et al.
Published: (2025)

Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language Models
by: Wang, Zehao, et al.
Published: (2024)

FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo Embeddings
by: Wang, Zhen, et al.
Published: (2023)

PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers
by: Liu, Dazhuang, et al.
Published: (2026)

Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Models
by: Wang, Lehan, et al.
Published: (2025)

MultiST: A Cross-Attention-Based Multimodal Model for Spatial Transcriptomic
by: Wang, Wei, et al.
Published: (2026)

LoRA Patching: Exposing the Fragility of Proactive Defenses against Deepfakes
by: Qu, Zuomin, et al.
Published: (2025)

Prototype Guided Backdoor Defense
by: Amula, Venkat Adithya, et al.
Published: (2025)

MTAttack: Multi-Target Backdoor Attacks against Large Vision-Language Models
by: Wang, Zihan, et al.
Published: (2025)

Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks
by: Wang, Lehan, et al.
Published: (2024)

Sparse Shortcuts: Facilitating Efficient Fusion in Multimodal Large Language Models
by: Zhang, Jingrui, et al.
Published: (2026)

Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding
by: Yu, Runpeng, et al.
Published: (2025)

Robust Defense Strategies for Multimodal Contrastive Learning: Efficient Fine-tuning Against Backdoor Attacks
by: Hossain, Md. Iqbal, et al.
Published: (2025)