# Mitigating the Impact of Attribute Editing on Face Recognition

Source: [Mitigating the Impact of Attribute Editing on Face Recognition](<https://www.sota2.com/research/paper/68fa72e01e209131cea591cc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:36:44.860Z

Authors: Sudipta Banerjee, Sai Pranaswi Mullangi, Shruti Wagle, Chinmay Hegde, Nasir Memon

Published: 2024-03-12T22:03:19.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2403.08092>)

[PDF](<https://arxiv.org/pdf/2403.08092.pdf>)
