[Submitted on 20 Sep 2024 (v1), last revised 30 Jul 2026 (this version, v3)]

View PDF HTML (experimental)

Abstract:The misuse of deep learning-based facial manipulation poses a serious threat to civil rights. To prevent such fraud at its source, proactive defense methods have been proposed that embed invisible adversarial perturbations into images, disrupting the manipulation process and rendering the forged output unconvincing to observers. However, non-targeted disruption of the output may leave identifiable facial features intact, potentially leading to the stigmatization of individuals. In this work, we propose a universal framework for combating facial manipulation, termed ID-Guard. The framework employs a single forward pass of an encoder-decoder network to generate cross-model transferable adversarial perturbations. We introduce a novel Identity Destruction Module (IDM) to suppress identifiable features in manipulated faces. The perturbation generation is optimized by formulating the disruption of various manipulation types as a multi-task learning problem, with a dynamic weighting strategy designed to enhance cross-model performance. Experimental results show that ID-Guard effectively defends against diverse facial manipulation models while degrading identifiable regions in manipulated images. It also enables disrupted images to evade facial inpainting and facial recognition systems. Moreover, ID-Guard can be seamlessly integrated as a plug-and-play component into other tasks, such as adversarial training. The source code is publicly available at this https URL.

Submission history

From: Zuomin Qu [view email]
[v1] Fri, 20 Sep 2024 09:30:08 UTC (4,124 KB)
[v2] Thu, 10 Apr 2025 07:58:51 UTC (4,376 KB)
[v3] Thu, 30 Jul 2026 02:30:32 UTC (3,989 KB)