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

2025-02-28 · CVPR 2025 1 · Haonan An, Guang Hua, Zhengru Fang, Guowen Xu, Susanto Rahardja, Yuguang Fang

The intellectual property of deep image-to-image models can be protected by the so-called box-free watermarking. It uses an encoder and a decoder, respectively, to embed into and extract from the model's output images invisible copyright marks. Prior works have improved watermark robustness, focusing on the design of better watermark encoders. In this paper, we reveal an overlooked vulnerability of the unprotected watermark decoder which is jointly trained with the encoder and can be exploited to train a watermark removal network. To defend against such an attack, we propose the decoder gradient shield (DGS) as a protection layer in the decoder API to prevent gradient-based watermark removal with a closed-form solution. The fundamental idea is inspired by the classical adversarial attack, but is utilized for the first time as a defensive mechanism in the box-free model watermarking. We then demonstrate that DGS can reorient and rescale the gradient directions of watermarked queries and stop the watermark remover's training loss from converging to the level without DGS, while retaining decoder output image quality. Experimental results verify the effectiveness of proposed method. Code of paper will be made available upon acceptance.

📄 PDF Abstract BibTeX arXiv:2502.20924

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack Decoder

Decoder Gradient Shields: A Family of Provable and High-Fidelity Methods Against Gradient-Based Box-Free Watermark Removal

2026-01-17 · Haonan An, Guang Hua, Wei Du, Hangcheng Cao 외 arxiv

Box-free model watermarking has gained significant attention in deep neural network (DNN) intellectual property protection due to its model-agnostic nature and its ability to flexibly manage high-entropy image outputs fr…

Image Generation

Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models

2026-02-12 · Alexander W. Goodall, Francesco Belardinelli arxiv

Reinforcement learning (RL) is a powerful framework for optimal decision-making and control but often lacks provable guarantees for safety-critical applications. In this paper, we introduce a novel recovery-based shieldi…

Reinforcement Learning Continuous Control

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

2026-07-30 · Cheng Wei arxiv

Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data. However, a recent attack, NeuroImprint [1] (arXiv:2606.20553), demonstrates that a malicious parameter serve…

Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning

2024-05-22 · Arko Banerjee, Kia Rahmani, Joydeep Biswas, Isil Dillig

Among approaches for provably safe reinforcement learning, Model Predictive Shielding (MPS) has proven effective at complex tasks in continuous, high-dimensional state spaces, by leveraging a backup policy to ensure safe…

reinforcement-learning Reinforcement Learning Safe Reinforcement Learning

Approximate Shielding of Atari Agents for Safe Exploration

2023-04-21 · Alexander W. Goodall, Francesco Belardinelli

Balancing exploration and conservatism in the constrained setting is an important problem if we are to use reinforcement learning for meaningful tasks in the real world. In this paper, we propose a principled algorithm f…

Atari Games Safe Exploration