Imagen de Portada

Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	An, Haonan, Hua, Guang, Fang, Zhengru, Xu, Guowen, Rahardja, Susanto, Fang, Yuguang
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

Decoder Gradient Shields: A Family of Provable and High-Fidelity Methods Against Gradient-Based Box-Free Watermark Removal
por: An, Haonan, et al.
Publicado: (2026)

Removing Box-Free Watermarks for Image-to-Image Models via Query-Based Reverse Engineering
por: An, Haonan, et al.
Publicado: (2025)

Box-Free Model Watermarks Are Prone to Black-Box Removal Attacks
por: An, Haonan, et al.
Publicado: (2024)

NWaaS: Nonintrusive Watermarking as a Service for X-to-Image DNN
por: An, Haonan, et al.
Publicado: (2025)

SmartCooper: Vehicular Collaborative Perception with Adaptive Fusion and Judger Mechanism
por: Zhang, Yuang, et al.
Publicado: (2024)

FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
por: Tao, Yihang, et al.
Publicado: (2026)

Secure Traffic Sign Recognition: An Attention-Enabled Universal Image Inpainting Mechanism against Light Patch Attacks
por: Cao, Hangcheng, et al.
Publicado: (2024)

RecoverMark: Robust Watermarking for Localization and Recovery of Manipulated Faces
por: An, Haonan, et al.
Publicado: (2026)

Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception
por: Tao, Yihang, et al.
Publicado: (2026)

Directed-CP: Directed Collaborative Perception for Connected and Autonomous Vehicles via Proactive Attention
por: Tao, Yihang, et al.
Publicado: (2024)

On the Provable Importance of Gradients for Language-Assisted Image Clustering
por: Peng, Bo, et al.
Publicado: (2025)

Collaborative Perception for Connected and Autonomous Driving: Challenges, Possible Solutions and Opportunities
por: Hu, Senkang, et al.
Publicado: (2024)

AgentsCoMerge: Large Language Model Empowered Collaborative Decision Making for Ramp Merging
por: Hu, Senkang, et al.
Publicado: (2024)

Task-Oriented Semantic Compression for Localization at the Network Edge
por: Fang, Zhengru, et al.
Publicado: (2025)

Towards Full-scene Domain Generalization in Multi-agent Collaborative Bird's Eye View Segmentation for Connected and Autonomous Driving
por: Hu, Senkang, et al.
Publicado: (2023)

CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs
por: Fang, Zhengru, et al.
Publicado: (2026)

MEDTalk: Multimodal Controlled 3D Facial Animation with Dynamic Emotions by Disentangled Embedding
por: Liu, Chang, et al.
Publicado: (2025)

Invisible Image Watermarks Are Provably Removable Using Generative AI
por: Zhao, Xuandong, et al.
Publicado: (2023)

Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
por: Yang, Zijin, et al.
Publicado: (2024)

DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation
por: Gong, Yan, et al.
Publicado: (2025)

GCP: Guarded Collaborative Perception with Spatial-Temporal Aware Malicious Agent Detection
por: Tao, Yihang, et al.
Publicado: (2025)

CP-Guard+: A New Paradigm for Malicious Agent Detection and Defense in Collaborative Perception
por: Hu, Senkang, et al.
Publicado: (2025)

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

Adversarial Watermarking for Face Recognition
por: Yao, Yuguang, et al.
Publicado: (2024)

Probability-Flow Distillation: Exact Wasserstein Gradient Flow for High-Fidelity 3D Generation
por: Ramanan, Rohith, et al.
Publicado: (2026)

The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition
por: Yuan, Shuai, et al.
Publicado: (2024)

Assessing the Efficacy of Invisible Watermarks in AI-Generated Medical Images
por: Xing, Xiaodan, et al.
Publicado: (2024)

DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation
por: Fang, Yingying, et al.
Publicado: (2024)

Hide and Seek: How Does Watermarking Impact Face Recognition?
por: Yao, Yuguang, et al.
Publicado: (2024)

QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution
por: Zhu, Libo, et al.
Publicado: (2025)

MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbation
por: Kong, Xiaoxi, et al.
Publicado: (2026)

Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategy
por: Bulychev, Maria, et al.
Publicado: (2026)

Gradient Descent Provably Solves Nonlinear Tomographic Reconstruction
por: Fridovich-Keil, Sara, et al.
Publicado: (2023)

Bootstrap Deep Spectral Clustering with Optimal Transport
por: Guo, Wengang, et al.
Publicado: (2025)

CP-uniGuard: A Unified, Probability-Agnostic, and Adaptive Framework for Malicious Agent Detection and Defense in Multi-Agent Embodied Perception Systems
por: Hu, Senkang, et al.
Publicado: (2025)

Structure-Guided Diffusion Models for High-Fidelity Portrait Shadow Removal
por: Yu, Wanchang, et al.
Publicado: (2025)

Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization
por: Fang, Hao, et al.
Publicado: (2026)

FFGAF-SNN: The Forward-Forward Based Gradient Approximation Free Training Framework for Spiking Neural Networks
por: Xu, Changqing, et al.
Publicado: (2025)

Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection
por: Guo, Yu, et al.
Publicado: (2025)

Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models
por: Kim, Donghoon, et al.
Publicado: (2025)