Imagen de Portada

RunawayEvil: Jailbreaking the Image-to-Video Generative Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Songping, Qian, Rufan, Lyu, Yueming, Liu, Qinglong, Zou, Linzhuang, Qin, Jie, Liu, Songhua, Shan, Caifeng
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts
por: Wang, Songping, et al.
Publicado: (2026)

An Effective End-to-End Solution for Multimodal Action Recognition
por: Wang, Songping, et al.
Publicado: (2025)

Exploring Adversarial Transferability between Kolmogorov-arnold Networks
por: Wang, Songping, et al.
Publicado: (2025)

Anti-Aesthetics: Protecting Facial Privacy against Customized Text-to-Image Synthesis
por: Wang, Songping, et al.
Publicado: (2025)

Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos
por: Wang, Songping, et al.
Publicado: (2025)

DiffusionAgent: Navigating Expert Models for Agentic Image Generation
por: Qin, Jie, et al.
Publicado: (2024)

VII: Visual Instruction Injection for Jailbreaking Image-to-Video Generation Models
por: Zheng, Bowen, et al.
Publicado: (2026)

AvatarBack: Back-Head Generation for Complete 3D Avatars from Front-View Images
por: Xin, Shiqi, et al.
Publicado: (2025)

DeltaSpace: A Semantic-aligned Feature Space for Flexible Text-guided Image Editing
por: Lyu, Yueming, et al.
Publicado: (2023)

ViBe: Ultra-High-Resolution Video Synthesis Born from Pure Images
por: Wu, Yunfeng, et al.
Publicado: (2026)

Video-Infinity: Distributed Long Video Generation
por: Tan, Zhenxiong, et al.
Publicado: (2024)

CoDA: From Text-to-Image Diffusion Models to Training-Free Dataset Distillation
por: Zhou, Letian, et al.
Publicado: (2025)

Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models
por: Ying, Zonghao, et al.
Publicado: (2026)

VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding
por: Yang, Ruoliu, et al.
Publicado: (2026)

Image Editing As Programs with Diffusion Models
por: Hu, Yujia, et al.
Publicado: (2025)

FreeSwim: Revisiting Sliding-Window Attention Mechanisms for Training-Free Ultra-High-Resolution Video Generation
por: Wu, Yunfeng, et al.
Publicado: (2025)

One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control
por: Rao, Haoxiang, et al.
Publicado: (2026)

ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer
por: Yu, Ruonan, et al.
Publicado: (2026)

GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
por: Gao, Xin, et al.
Publicado: (2025)

Text-guided Controllable Diffusion for Realistic Camouflage Images Generation
por: Qian, Yuhang, et al.
Publicado: (2025)

Control and Realism: Best of Both Worlds in Layout-to-Image without Training
por: Li, Bonan, et al.
Publicado: (2025)

LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions
por: Zhang, Tianyuan, et al.
Publicado: (2024)

Uncertainty-Aware Concept and Motion Segmentation for Semi-Supervised Angiography Videos
por: Luo, Yu, et al.
Publicado: (2026)

Beyond Visual Safety: Jailbreaking Multimodal Large Language Models for Harmful Image Generation via Semantic-Agnostic Inputs
por: Yu, Mingyu, et al.
Publicado: (2026)

NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing
por: Pan, Tianlin, et al.
Publicado: (2026)

Perception-guided Jailbreak against Text-to-Image Models
por: Huang, Yihao, et al.
Publicado: (2024)

LoVoRA: Text-guided and Mask-free Video Object Removal and Addition with Learnable Object-aware Localization
por: Xiao, Zhihan, et al.
Publicado: (2025)

CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
por: Liu, Songhua, et al.
Publicado: (2024)

Free-DyGS: Camera-Pose-Free Scene Reconstruction for Dynamic Surgical Videos with Gaussian Splatting
por: Li, Qian, et al.
Publicado: (2024)

MultiAnimate: Pose-Guided Image Animation Made Extensible
por: Hu, Yingcheng, et al.
Publicado: (2026)

LinFusion: 1 GPU, 1 Minute, 16K Image
por: Liu, Songhua, et al.
Publicado: (2024)

TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
por: Zou, Quanchen, et al.
Publicado: (2026)

Rethinking Large-scale Dataset Compression: Shifting Focus From Labels to Images
por: Xiao, Lingao, et al.
Publicado: (2025)

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey
por: Liu, Xuannan, et al.
Publicado: (2024)

InstaFace: Identity-Preserving Facial Editing with Single Image Inference
por: Khan, MD Wahiduzzaman, et al.
Publicado: (2025)

MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation
por: Yu, Zhiping, et al.
Publicado: (2024)

Two Frames Matter: A Temporal Attack for Text-to-Video Model Jailbreaking
por: Chen, Moyang, et al.
Publicado: (2026)

Research on fusing topological data analysis with convolutional neural network
por: Han, Yang, et al.
Publicado: (2024)

EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
por: Liu, Yaofang, et al.
Publicado: (2023)

HAGAN: Hybrid Augmented Generative Adversarial Network for Medical Image Synthesis
por: Ju, Zhihan, et al.
Publicado: (2024)