iFADIT: Invertible Face Anonymization via Disentangled Identity Transform

2025-01-08

AI Summary

Existing face anonymization methods struggle to simultaneously ensure privacy protection, visual fidelity, and forensic recoverability. Method: This paper proposes the first key-controllable anonymization framework integrating invertible flow-based models with disentangled identity representation. It introduces an identity-attribute disentangling encoder, couples invertible flow transformations with a StyleGAN generator, and employs a two-stage key-aware training strategy to enable precise bidirectional mapping between anonymized and original faces. Contributions/Results: (1) It achieves the first secure and verifiably invertible anonymization; (2) it supports lossless, key-dependent identity recovery while preserving high visual naturalness and diversity; (3) it outperforms state-of-the-art methods comprehensively in anonymity, reconstruction accuracy, security, and interpretability—thereby meeting real-world requirements for privacy compliance and judicial forensics.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Philosophy and Ethics of AI: Privacy & Security

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Face anonymization aims to conceal the visual identity of a face to safeguard the individual's privacy. Traditional methods like blurring and pixelation can largely remove identifying features, but these techniques significantly degrade image quality and are vulnerable to deep reconstruction attacks. Generative models have emerged as a promising solution for anonymizing faces while preserving a natural appearance.However, many still face limitations in visual quality and often overlook the potential to recover the original face from the anonymized version, which can be valuable in specific contexts such as image forensics. This paper proposes a novel framework named iFADIT, an acronym for Invertible Face Anonymization via Disentangled Identity Transform.The framework features a disentanglement architecture coupled with a secure flow-based model: the former decouples identity information from non-identifying attributes, while the latter transforms the decoupled identity into an anonymized version in an invertible manner controlled by a secret key. The anonymized face can then be reconstructed based on a pre-trained StyleGAN that ensures high image quality and realistic facial details. Recovery of the original face (aka de-anonymization) is possible upon the availability of the matching secret, by inverting the anonymization process based on the same set of model parameters. Furthermore, a dedicated secret-key mechanism along with a dual-phase training strategy is devised to ensure the desired properties of face anonymization. Qualitative and quantitative experiments demonstrate the superiority of the proposed approach in anonymity, reversibility, security, diversity, and interpretability over competing methods.

Problem

• Facial Anonymization
• Privacy Protection
• Reversible Recovery

Innovation

• Facial Anonymization
• Reversible Process
• Generative Model