Mitigating the Impact of Attribute Editing on Face Recognition
This addresses a critical security and reliability issue for automated face recognition systems used in applications like surveillance and authentication, representing an incremental improvement over existing editing methods.
The paper tackles the problem that facial attribute editing with generative AI models severely degrades face recognition systems, even with identity-preserving models, and proposes novel local and global editing techniques that outperform state-of-the-art methods like BLIP and InstantID while significantly improving identity retention.
Through a large-scale study over diverse face images, we show that facial attribute editing using modern generative AI models can severely degrade automated face recognition systems. This degradation persists even with identity-preserving generative models. To mitigate this issue, we propose two novel techniques for local and global attribute editing. We empirically ablate twenty-six facial semantic, demographic and expression-based attributes that have been edited using state-of-the-art generative models, and evaluate them using ArcFace and AdaFace matchers on CelebA, CelebAMaskHQ and LFW datasets. Finally, we use LLaVA, an emerging visual question-answering framework for attribute prediction to validate our editing techniques. Our methods outperform the current state-of-the-art at facial editing (BLIP, InstantID) while improving identity retention by a significant extent.