paper-with-me

Papers

DIP-Watermark: A Double Identity Protection Method Based on Robust Adversarial Watermark

2024-04-23 · Yunming Zhang, Dengpan Ye, Caiyun Xie, Sipeng Shen, Ziyi Liu, Jiacheng Deng, Long Tang

The wide deployment of Face Recognition (FR) systems poses privacy risks. One countermeasure is adversarial attack, deceiving unauthorized malicious FR, but it also disrupts regular identity verification of trusted authorizers, exacerbating the potential threat of identity impersonation. To address this, we propose the first double identity protection scheme based on traceable adversarial watermarking, termed DIP-Watermark. DIP-Watermark employs a one-time watermark embedding to deceive unauthorized FR models and allows authorizers to perform identity verification by extracting the watermark. Specifically, we propose an information-guided adversarial attack against FR models. The encoder embeds an identity-specific watermark into the deep feature space of the carrier, guiding recognizable features of the image to deviate from the source identity. We further adopt a collaborative meta-optimization strategy compatible with sub-tasks, which regularizes the joint optimization direction of the encoder and decoder. This strategy enhances the representation of universal carrier features, mitigating multi-objective optimization conflicts in watermarking. Experiments confirm that DIP-Watermark achieves significant attack success rates and traceability accuracy on state-of-the-art FR models, exhibiting remarkable robustness that outperforms the existing privacy protection methods using adversarial attacks and deep watermarking, or simple combinations of the two. Our work potentially opens up new insights into proactive protection for FR privacy.

📄 PDF Abstract BibTeX arXiv:2404.14693

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackDecoderFace Recognition

Methods 이 논문이 사용한 방법론

DPG Deterministic Policy Gradient, or DPG, is a policy gradient method for reinforcement learning. Instead of the policy function $\pi\left(.\mid{s}\right)$ being modeled as a…

Similar Papers 제목 키워드 기반

Protecting the Intellectual Properties of Deep Neural Networks with an Additional Class and Steganographic Images

2021-04-19 · Shichang Sun, Mingfu Xue, Jian Wang, Weiqiang Liu

Recently, the research on protecting the intellectual properties (IP) of deep neural networks (DNN) has attracted serious concerns. A number of DNN copyright protection methods have been proposed. However, most of the ex…

Image SteganographyManagement

Conceptwm: A Diffusion Model Watermark for Concept Protection

2024-11-18 · Liangqi Lei, Keke Gai, Jing Yu, Liehuang Zhu 외

The personalization techniques of diffusion models succeed in generating specific concepts but also pose threats to copyright protection and illegal use. Model Watermarking is an effective method to prevent the unauthori…

Image Generation

A Robust Document Image Watermarking Scheme using Deep Neural Network

2022-02-26 · Sulong Ge, Zhihua Xia, Jianwei Fei, Xingming Sun 외

Watermarking is an important copyright protection technology which generally embeds the identity information into the carrier imperceptibly. Then the identity can be extracted to prove the copyright from the watermarked …

Decoder

Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning

2024-02-22 · Shen Li, Liuyi Yao, Jinyang Gao, Lan Zhang 외

To support various applications, a prevalent and efficient approach for business owners is leveraging their valuable datasets to fine-tune a pre-trained LLM through the API provided by LLM owners or cloud servers. Howeve…

ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization

2024-11-06 · Huayang Huang, Yu Wu, Qian Wang

Watermarking generative content serves as a vital tool for authentication, ownership protection, and mitigation of potential misuse. Existing watermarking methods face the challenge of balancing robustness and concealmen…