Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908689222336512 |
|---|---|
| author | Lin, Kaiqing Yan, Zhiyuan Zhang, Ke-Yue Hao, Li Zhou, Yue Lin, Yuzhen Li, Weixiang Yao, Taiping Ding, Shouhong Li, Bin |
| author_facet | Lin, Kaiqing Yan, Zhiyuan Zhang, Ke-Yue Hao, Li Zhou, Yue Lin, Yuzhen Li, Weixiang Yao, Taiping Ding, Shouhong Li, Bin |
| contents | Securing personal identity against deepfake attacks is increasingly critical in the digital age, especially for celebrities and political figures whose faces are easily accessible and frequently targeted. Most existing deepfake detection methods focus on general-purpose scenarios and often ignore the valuable prior knowledge of known facial identities, e.g., "VIP individuals" whose authentic facial data are already available. In this paper, we propose \textbf{VIPGuard}, a unified multimodal framework designed to capture fine-grained and comprehensive facial representations of a given identity, compare them against potentially fake or similar-looking faces, and reason over these comparisons to make accurate and explainable predictions. Specifically, our framework consists of three main stages. First, fine-tune a multimodal large language model (MLLM) to learn detailed and structural facial attributes. Second, we perform identity-level discriminative learning to enable the model to distinguish subtle differences between highly similar faces, including real and fake variations. Finally, we introduce user-specific customization, where we model the unique characteristics of the target face identity and perform semantic reasoning via MLLM to enable personalized and explainable deepfake detection. Our framework shows clear advantages over previous detection works, where traditional detectors mainly rely on low-level visual cues and provide no human-understandable explanations, while other MLLM-based models often lack a detailed understanding of specific face identities. To facilitate the evaluation of our method, we built a comprehensive identity-aware benchmark called \textbf{VIPBench} for personalized deepfake detection, involving the latest 7 face-swapping and 7 entire face synthesis techniques for generation. The code is available at https://github.com/KQL11/VIPGuard . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19582 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes Lin, Kaiqing Yan, Zhiyuan Zhang, Ke-Yue Hao, Li Zhou, Yue Lin, Yuzhen Li, Weixiang Yao, Taiping Ding, Shouhong Li, Bin Computer Vision and Pattern Recognition Securing personal identity against deepfake attacks is increasingly critical in the digital age, especially for celebrities and political figures whose faces are easily accessible and frequently targeted. Most existing deepfake detection methods focus on general-purpose scenarios and often ignore the valuable prior knowledge of known facial identities, e.g., "VIP individuals" whose authentic facial data are already available. In this paper, we propose \textbf{VIPGuard}, a unified multimodal framework designed to capture fine-grained and comprehensive facial representations of a given identity, compare them against potentially fake or similar-looking faces, and reason over these comparisons to make accurate and explainable predictions. Specifically, our framework consists of three main stages. First, fine-tune a multimodal large language model (MLLM) to learn detailed and structural facial attributes. Second, we perform identity-level discriminative learning to enable the model to distinguish subtle differences between highly similar faces, including real and fake variations. Finally, we introduce user-specific customization, where we model the unique characteristics of the target face identity and perform semantic reasoning via MLLM to enable personalized and explainable deepfake detection. Our framework shows clear advantages over previous detection works, where traditional detectors mainly rely on low-level visual cues and provide no human-understandable explanations, while other MLLM-based models often lack a detailed understanding of specific face identities. To facilitate the evaluation of our method, we built a comprehensive identity-aware benchmark called \textbf{VIPBench} for personalized deepfake detection, involving the latest 7 face-swapping and 7 entire face synthesis techniques for generation. The code is available at https://github.com/KQL11/VIPGuard . |
| title | Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.19582 |