DiffClean: Diffusion-based Makeup Removal for Accurate Age Estimation
This addresses the issue of protecting underage users from unauthorized access to age-restricted online platforms by defending against makeup attacks, representing an incremental improvement over existing methods.
The paper tackled the problem of accurate age estimation being confounded by facial makeup, which can fool systems, by proposing DiffClean, a diffusion-based makeup removal method that improved minor vs. adult accuracy by 4.8% and face verification TMR by 8.9% at FMR=0.01%.
Accurate age verification can protect underage users from unauthorized access to online platforms and e-commerce sites that provide age-restricted services. However, accurate age estimation can be confounded by several factors, including facial makeup that can induce changes to alter perceived identity and age to fool both humans and machines. In this work, we propose DiffClean which erases makeup traces using a text-guided diffusion model to defend against makeup attacks. DiffClean improves age estimation (minor vs. adult accuracy by 4.8%) and face verification (TMR by 8.9% at FMR=0.01%) over competing baselines on digitally simulated and real makeup images.