Image de couverture de livre

When One Modality Rules Them All: Backdoor Modality Collapse in Multimodal Diffusion Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Qitong, Dai, Haoran, Zhang, Haotian, Rasmussen, Christopher, Wang, Binghui
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

TabPFN: One Model to Rule Them All?
par: Zhang, Qiong, et autres
Publié: (2025)

Backdoor Attacks on Discrete Graph Diffusion Models
par: Wang, Jiawen, et autres
Publié: (2025)

One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them
par: Holmov, Ali, et autres
Publié: (2026)

One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications
par: Lyu, Mengyao, et autres
Publié: (2023)

One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models
par: Jing, Zilin, et autres
Publié: (2026)

One Period to Rule Them All: Identifying Critical Learning Periods in Deep Networks
par: Fukase, Vinicius Yuiti, et autres
Publié: (2025)

One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning
par: Li, Yiyuan, et autres
Publié: (2026)

One Model to Forecast Them All and in Entity Distributions Bind Them
par: Bölat, Kutay, et autres
Publié: (2025)

Beyond Modality Collapse: Representations Blending for Multimodal Dataset Distillation
par: Zhang, Xin, et autres
Publié: (2025)

One RNG to Rule Them All: How Randomness Becomes an Attack Vector in Machine Learning
par: Prabhu, Kotekar Annapoorna, et autres
Publié: (2026)

OneLLM: One Framework to Align All Modalities with Language
par: Han, Jiaming, et autres
Publié: (2023)

Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics
par: Downer, Jane, et autres
Publié: (2024)

One Noise to Rule Them All: Learning a Unified Model of Spatially-Varying Noise Patterns
par: Maesumi, Arman, et autres
Publié: (2024)

One Framework to Rule Them All: Unifying RL-Based and RL-Free Methods in RLHF
par: Cai, Xin
Publié: (2025)

Addressing Missing and Noisy Modalities in One Solution: Unified Modality-Quality Framework for Low-quality Multimodal Data
par: Mai, Sijie, et autres
Publié: (2026)

Modality Collapse as Mismatched Decoding: Information-Theoretic Limits of Multimodal LLMs
par: Billa, Jayadev
Publié: (2026)

Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models
par: Wan, Guangnian, et autres
Publié: (2026)

Cross-Modality Controlled Molecule Generation with Diffusion Language Model
par: Zhang, Yunzhe, et autres
Publié: (2025)

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP
par: Xu, Binyan, et autres
Publié: (2025)

Measuring Cross-Modal Interactions in Multimodal Models
par: Wenderoth, Laura, et autres
Publié: (2024)

One Set to Rule Them All: How to Obtain General Chemical Conditions via Bayesian Optimization over Curried Functions
par: Schmid, Stefan P., et autres
Publié: (2025)

OVA-IB: One vs All Information Bottleneck for Multi-Modal Alignment
par: Li, Tianchao, et autres
Publié: (2026)

Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data
par: Zhang, Yuhui, et autres
Publié: (2024)

No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets
par: Coupette, Corinna, et autres
Publié: (2025)

One Operator to Rule Them All? On Boundary-Indexed Operator Families in Neural PDE Solvers
par: Shikhman, Lennon J.
Publié: (2026)

Mitigating Modality Quantity and Quality Imbalance in Multimodal Online Federated Learning
par: Wang, Heqiang, et autres
Publié: (2025)

A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide Generation
par: Wang, Yongkang, et autres
Publié: (2023)

SCULPT: Constraint-Guided Pruned MCTS that Carves Efficient Paths for Mathematical Reasoning
par: Fang, Qitong, et autres
Publié: (2026)

The Design Space of Tri-Modal Masked Diffusion Models
par: Bethune, Louis, et autres
Publié: (2026)

Cross-Modal Prototype based Multimodal Federated Learning under Severely Missing Modality
par: Le, Huy Q., et autres
Publié: (2024)

Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learning
par: Zheng, Wugeng, et autres
Publié: (2026)

MMOne: Representing Multiple Modalities in One Scene
par: Gu, Zhifeng, et autres
Publié: (2025)

MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models
par: Wang, Xiaolong, et autres
Publié: (2025)

OneProt: Towards Multi-Modal Protein Foundation Models
par: Flöge, Klemens, et autres
Publié: (2024)

When Tabular Foundation Models Transfer Across Modalities: A Systematic Evaluation Across 95 Datasets, 7 Modalities, and Two Regimes
par: Lafrance, Julien
Publié: (2026)

Communication-Efficient Multimodal Federated Learning: Joint Modality and Client Selection
par: Yuan, Liangqi, et autres
Publié: (2024)

Controllable Motion Generation via Diffusion Modal Coupling
par: Wang, Luobin, et autres
Publié: (2025)

One Wave To Explain Them All: A Unifying Perspective On Feature Attribution
par: Kasmi, Gabriel, et autres
Publié: (2024)

MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion
par: Zheng, Wugeng, et autres
Publié: (2026)

SEAnet: A Deep Learning Architecture for Data Series Similarity Search
par: Wang, Qitong, et autres
Publié: (2026)