Image de couverture de livre

Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Yu-Feng, Huang, Tzuhsuan, Chiu, Pin-Yen, Chen, Jun-Cheng
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

Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack
par: Wang, Ruofei, et autres
Publié: (2024)

Enhancing Robustness in Post-Processing Watermarking: An Ensemble Attack Network Using CNNs and Transformers
par: Huang, Tzuhsuan, et autres
Publié: (2025)

BlenDA: Domain Adaptive Object Detection through diffusion-based blending
par: Huang, Tzuhsuan, et autres
Publié: (2024)

Text Slider: Efficient and Plug-and-Play Continuous Concept Control for Image/Video Synthesis via LoRA Adapters
par: Chiu, Pin-Yen, et autres
Publié: (2025)

Backdoor Attack with Sparse and Invisible Trigger
par: Gao, Yinghua, et autres
Publié: (2023)

WMCopier: Forging Invisible Image Watermarks on Arbitrary Images
par: Dong, Ziping, et autres
Publié: (2025)

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
par: Chou, Sheng-Yen, et autres
Publié: (2023)

WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language Models
par: Yang, Zijin, et autres
Publié: (2026)

Safe-SD: Safe and Traceable Stable Diffusion with Text Prompt Trigger for Invisible Generative Watermarking
par: Ma, Zhiyuan, et autres
Publié: (2024)

Invisible Watermarks: Attacks and Robustness
par: Hwang, Dongjun, et autres
Publié: (2024)

An Invisible Backdoor Attack Based On Semantic Feature
par: Chen, Yangming
Publié: (2024)

Invisible Backdoor Attacks on Diffusion Models
par: Li, Sen, et autres
Publié: (2024)

Invisible Clean-Label Backdoor Attacks for Generative Data Augmentation
par: Xiang, Ting, et autres
Publié: (2026)

StyleDiT: A Unified Framework for Diverse Child and Partner Faces Synthesis with Style Latent Diffusion Transformer
par: Chiu, Pin-Yen, et autres
Publié: (2024)

RAVEN: Erasing Invisible Watermarks via Novel View Synthesis
par: Shamshad, Fahad, et autres
Publié: (2026)

ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
par: Huang, Huayang, et autres
Publié: (2024)

Are Watermarked Images Editable? SafeMark for Watermark-Preserving Text-Guided Image Editing
par: Wu, Xiaodong, et autres
Publié: (2026)

OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking
par: Zhang, Xuanyu, et autres
Publié: (2024)

Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
par: Chin, Zhi-Yi, et autres
Publié: (2023)

Gen-n-Val: Agentic Image Data Generation and Validation
par: Huang, Jing-En, et autres
Publié: (2025)

Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models
par: Zhang, Jie, et autres
Publié: (2025)

Diffusion-Based Image Editing for Breaking Robust Watermarks
par: Ni, Yunyi, et autres
Publié: (2025)

Backdoor Directions in Vision Transformers
par: Karayalcin, Sengim, et autres
Publié: (2026)

Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger
par: Yu, Yi, et autres
Publié: (2024)

Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors
par: Abad, Gorka, et autres
Publié: (2026)

FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
par: Guo, Yiyang, et autres
Publié: (2024)

Invisible Backdoor Attack against Self-supervised Learning
par: Zhang, Hanrong, et autres
Publié: (2024)

A Watermark for Auto-Regressive Image Generation Models
par: Wu, Yihan, et autres
Publié: (2025)

Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting
par: Chin, Zhi-Yi, et autres
Publié: (2024)

EditInfinity: Image Editing with Binary-Quantized Generative Models
par: Wang, Jiahuan, et autres
Publié: (2025)

Invisible Image Watermarks Are Provably Removable Using Generative AI
par: Zhao, Xuandong, et autres
Publié: (2023)

SpecGuard: Spectral Projection-based Advanced Invisible Watermarking
par: Alam, Inzamamul, et autres
Publié: (2025)

Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
par: Li, Zida, et autres
Publié: (2026)

Assessing the Efficacy of Invisible Watermarks in AI-Generated Medical Images
par: Xing, Xiaodan, et autres
Publié: (2024)

REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
par: Chen, Yukun, et autres
Publié: (2025)

DDI-CoCo: A Dataset For Understanding The Effect Of Color Contrast In Machine-Assisted Skin Disease Detection
par: Chiu, Ming-Chang, et autres
Publié: (2024)

Geometric Image Synchronization with Deep Watermarking
par: Fernandez, Pierre, et autres
Publié: (2025)

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
par: Li, Juncheng, et autres
Publié: (2025)

Drag within Prior Distribution: Text-Conditioned Point-Based Image Editing within Distribution Constraints
par: Hu, Haoyang, et autres
Publié: (2026)

Deep Robust Reversible Watermarking
par: Chen, Jiale, et autres
Publié: (2025)