FGMIA: Feature-Guided Model Inversion Attacks Against Face Recognition Models

Ye Lu, Shen Wang, Guopu Zhu, Zhaoyang Zhang, Jiwu Huang

Abstract: Model Inversion Attacks (MIAs) against face recognition systems aim to reconstruct facial images of specific individuals from the recognition models. Existing MIA approaches commonly optimize the latent variables of Generative Adversarial Networks (GANs) iteratively, which can result in non-smooth optimizations due to the complexity and entanglement of latent space. Furthermore, the optimization guided by the target model’s gradients may generate high-confidence images with poor perceptual similarity to the target class. This paper introduces a novel perspective by reformulating the inversion attack as a conditional data distribution learning task. Based on this, we propose a Feature-Guided Model Inversion Attack (FGMIA), which learns the facial data distribution and integrates feature guidance as a conditional signal. Specifically, we treat the deconstructed target model as a feature encoder, which provides guidance during the training of a specialized feature-guided diffusion model. During the attack, feature encodings implicit in the target model are extracted and utilized to guide the reconstruction of private data. Extensive experiments demonstrate that FGMIA accurately reconstructs private data from face recognition models and significantly improves evaluation accuracy and perceptual similarity compared to state-of-the-art methods while maintaining comparable target confidence scores. Our code is available at https://github.com/MMCTTT/FGMIA_codes

External IDs:dblp:journals/tifs/LuWZZH25