Image de couverture de livre

CoDefend: Cross-Modal Collaborative Defense via Diffusion Purification and Prompt Optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhu, Fengling, Liu, Boshi, Hua, Jingyu, Zhong, Sheng
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PromptFlare: Prompt-Generalized Defense via Cross-Attention Decoy in Diffusion-Based Inpainting
par: Na, Hohyun, et autres
Publié: (2025)

Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification
par: Yang, Wenkui, et autres
Publié: (2025)

Manipulating Multimodal Agents via Cross-Modal Prompt Injection
par: Wang, Le, et autres
Publié: (2025)

CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation
par: Hao, Haihong, et autres
Publié: (2025)

Robust and Efficient Adversarial Defense in SNNs via Image Purification and Joint Detection
par: Chen, Weiran, et autres
Publié: (2024)

GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
par: Yang, Yijun, et autres
Publié: (2024)

Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation
par: Yang, Hongtao, et autres
Publié: (2025)

Event-based Video Person Re-identification via Cross-Modality and Temporal Collaboration
par: Li, Renkai, et autres
Publié: (2025)

Enhancing Facial Privacy Protection via Weakening Diffusion Purification
par: Salar, Ali, et autres
Publié: (2025)

CoVAR: Co-generation of Video and Action for Robotic Manipulation via Multi-Modal Diffusion
par: Yang, Liudi, et autres
Publié: (2025)

ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt
par: Zeng, Fanhu, et autres
Publié: (2024)

Attack for Defense: Adversarial Agents for Point Prompt Optimization Empowering Segment Anything Model
par: Liu, Xueyu, et autres
Publié: (2025)

Prompt Diffusion Robustifies Any-Modality Prompt Learning
par: Du, Yingjun, et autres
Publié: (2024)

PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks
par: Guo, Ping, et autres
Publié: (2024)

Cross-Modal Retrieval for Motion and Text via DropTriple Loss
par: Yan, Sheng, et autres
Publié: (2023)

Federated Cross-Modal Style-Aware Prompt Generation
par: Prasad, Suraj, et autres
Publié: (2025)

Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery
par: Zheng, Haiyang, et autres
Publié: (2024)

PromptMAD: Cross-Modal Prompting for Multi-Class Visual Anomaly Localization
par: McCain, Duncan, et autres
Publié: (2026)

Multi-Prompt with Depth Partitioned Cross-Modal Learning
par: Tian, Yingjie, et autres
Publié: (2023)

Progressive Prompt-Guided Cross-Modal Reasoning for Referring Image Segmentation
par: Li, Jiachen, et autres
Publié: (2026)

AOEPT: Breaking the Implicit Modality-Reduction Bottleneck in Modality-Missing Prompt Tuning
par: Lang, Jian, et autres
Publié: (2026)

InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration
par: Yang, Zhongyu, et autres
Publié: (2025)

Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
par: Li, Yiquan, et autres
Publié: (2024)

Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning
par: Zhang, Zhifang, et autres
Publié: (2024)

DiffusionUavLoc: Visually Prompted Diffusion for Cross-View UAV Localization
par: Liu, Tao, et autres
Publié: (2025)

Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers
par: Lv, Zhengyao, et autres
Publié: (2025)

PROMISE: Prompt-Attentive Hierarchical Contrastive Learning for Robust Cross-Modal Representation with Missing Modalities
par: Chen, Jiajun, et autres
Publié: (2025)

Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo
par: Xu, Ninghui, et autres
Publié: (2026)

GDTS: Goal-Guided Diffusion Model with Tree Sampling for Multi-Modal Pedestrian Trajectory Prediction
par: Sun, Ge, et autres
Publié: (2023)

Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration
par: Zhao, Shu, et autres
Publié: (2024)

SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
par: Yang, Zhongyu, et autres
Publié: (2026)

PromptHash: Affinity-Prompted Collaborative Cross-Modal Learning for Adaptive Hashing Retrieval
par: Zou, Qiang, et autres
Publié: (2025)

Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation
par: Li, Xinyao, et autres
Publié: (2024)

Generalizing Vision-Language Models with Dedicated Prompt Guidance
par: Li, Xinyao, et autres
Publié: (2025)

Defending Against Frequency-Based Attacks with Diffusion Models
par: Amerehi, Fatemeh, et autres
Publié: (2025)

Adaptive Physical-Facial Representation Fusion via Subject-Invariant Cross-Modal Prompt Tuning for Video-Based Emotion Recognition
par: Luo, Xiwen, et autres
Publié: (2026)

Cross-Domain Few-Shot Learning via Multi-View Collaborative Optimization with Vision-Language Models
par: Chen, Dexia, et autres
Publié: (2025)

V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning
par: Hua, Hang, et autres
Publié: (2024)

Rad-VLSM: A Cross-Modal Framework with Semantics-Assisted Prompting for Medical Segmentation and Diagnosis
par: Zhang, Fengyi, et autres
Publié: (2026)

Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
par: Liu, Yiming, et autres
Publié: (2024)