AI-Powered Facial Mask Removal Is Not Suitable For Identification
Not on the map. Why?
Abstract (arXiv)
Recently, crowd-sourced online criminal investigations have used generative-AI to enhance low-quality visual evidence. In one high-profile case, social-media users circulated an "AI-unmasked" image of a federal agent involved in a fatal shooting, fueling a wide-spread misidentification. In response to this and similar incidents, we conducted a large-scale analysis evaluating the efficacy and risks of commercial AI-powered facial unmasking, specifically assessing whether the resulting faces can be reliably matched to true identities.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 2 of its 13 references that are in the map. First posted on arXiv 29 Mar 2026.
Builds on
2 of 13 references.
References · 2
- 2017VGGFace2: A dataset for recognising faces across pose and agecited by 914
- 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 391
Built on by
Not cited yet.