Cover Image

RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Ruofan, Ma, Xingjun
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

White-box Multimodal Jailbreaks Against Large Vision-Language Models
by: Wang, Ruofan, et al.
Published: (2024)

Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models
by: Wang, Ruofan, et al.
Published: (2025)

TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models
by: Wang, Xin, et al.
Published: (2026)

JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
by: Song, Jiaxin, et al.
Published: (2025)

A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models
by: Shuai, Xincheng, et al.
Published: (2024)

BadPatch: Diffusion-Based Generation of Physical Adversarial Patches
by: Wang, Zhixiang, et al.
Published: (2024)

IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves
by: Wang, Ruofan, et al.
Published: (2024)

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

FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models
by: Zhai, Kun, et al.
Published: (2025)

TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
by: Wang, Xin, et al.
Published: (2024)

Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey
by: Lamba, Preeti, et al.
Published: (2025)

DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
by: Zeng, Lunbin, et al.
Published: (2025)

Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models
by: Zhao, Yunhan, et al.
Published: (2025)

dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning
by: Ma, Yingzi, et al.
Published: (2025)

SIDE: Surrogate Conditional Data Extraction from Diffusion Models
by: Chen, Yunhao, et al.
Published: (2024)

MMaDA: Multimodal Large Diffusion Language Models
by: Yang, Ling, et al.
Published: (2025)

dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought
by: Wen, Junjie, et al.
Published: (2025)

WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language Models
by: Yang, Zijin, et al.
Published: (2026)

RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning
by: Xu, Jingqi, et al.
Published: (2025)

DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understanding
by: Ran, Lingyan, et al.
Published: (2025)

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process
by: Chen, Jiayi, et al.
Published: (2025)

Masked Diffusion Vision-Language Models for Temporal Action Localization
by: Wang, Fengshun, et al.
Published: (2026)

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

VideoMat: Extracting PBR Materials from Video Diffusion Models
by: Munkberg, Jacob, et al.
Published: (2025)

Adversarial Prompt Distillation for Vision-Language Models
by: Luo, Lin, et al.
Published: (2024)

IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
by: Guo, Jiayi, et al.
Published: (2025)

SafeVid: Toward Safety Aligned Video Large Multimodal Models
by: Wang, Yixu, et al.
Published: (2025)

MARE: Multimodal Alignment and Reinforcement for Explainable Deepfake Detection via Vision-Language Models
by: Xu, Wenbo, et al.
Published: (2026)

Hierarchical Vision-Language Alignment for Text-to-Image Generation via Diffusion Models
by: Johnson, Emily, et al.
Published: (2025)

Adversarial Prompt Tuning for Vision-Language Models
by: Zhang, Jiaming, et al.
Published: (2023)

Analyzing Diffusion and Autoregressive Vision Language Models in Multimodal Embedding Space
by: Wang, Zihang, et al.
Published: (2026)

Extracting Training Data from Unconditional Diffusion Models
by: Chen, Yunhao, et al.
Published: (2024)

Controllable Weather Synthesis and Removal with Video Diffusion Models
by: Lin, Chih-Hao, et al.
Published: (2025)

Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners
by: He, Xuehai, et al.
Published: (2023)

GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability Optimization
by: Pan, Yu, et al.
Published: (2026)

BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
by: Zhao, Yunhan, et al.
Published: (2024)

Early Failure Detection and Intervention in Video Diffusion Models
by: Byung-Ki, Kwon, et al.
Published: (2026)

DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models
by: Liang, Ruofan, et al.
Published: (2025)

Auditing Data Provenance in Real-world Text-to-Image Diffusion Models for Privacy and Copyright Protection
by: Zhu, Jie, et al.
Published: (2025)

Novel Diffusion Models for Multimodal 3D Hand Trajectory Prediction
by: Ma, Junyi, et al.
Published: (2025)