# MBZUAI and Khalifa University test FaceGuardian against AI image edits > The face-image method reduced identity similarity after edits by the diffusion models tested in the study. - Canonical URL: https://newsverum.com/en/news/mbzuai-faceguardian-image-identity-protection-2026 - Publisher: Newsverum - Section: Technology - Country: United Arab Emirates - Published: 2026-10-20T14:20:10+00:00 - Updated: 2026-10-20T14:20:10+00:00 - Event / data period: 2026-10-02 - Other editions: [Türkçe](https://newsverum.com/tr/news/mbzuai-faceguardian-image-identity-protection-2026.md), [العربية](https://newsverum.com/ar/news/mbzuai-faceguardian-image-identity-protection-2026.md), [Français](https://newsverum.com/fr/news/mbzuai-faceguardian-image-identity-protection-2026.md), [Español](https://newsverum.com/es/news/mbzuai-faceguardian-image-identity-protection-2026.md), [Deutsch](https://newsverum.com/de/news/mbzuai-faceguardian-image-identity-protection-2026.md), [Português](https://newsverum.com/pt/news/mbzuai-faceguardian-image-identity-protection-2026.md) Researchers at MBZUAI and Khalifa University developed FaceGuardian, a method intended to make it harder for diffusion models to preserve a person’s identity while editing face images. It adds facial details that remain visually similar to the original for people but can confuse machine recognition, and is designed to withstand image resizing and compression. In a celebrity-dataset experiment described by MBZUAI on 2 October, edited images were evaluated with face-recognition software. FaceGuardian recorded an FR similarity score of 0.272, compared with 0.833 for unprotected images; after compression, its score was 0.361, while the compared FaceLock method scored 0.709. The results apply to the open-source models and dataset tested by the researchers and do not guarantee protection with closed models or in every real-world condition. ## Data ### FaceGuardian experiment Evaluation of the identity-protection experiment Methodology: The unit registry has no matching unit for FR similarity scores; figures remain in the story text with dataset and comparison context. Results are specific to the source-stated model, edit and benchmark-dataset conditions; no cross-model or cross-country comparison or aggregation is made. | date | label | description | status | |---|---|---|---| | 2026-10-02 | Research findings published | The study reports model results under the synthetic or controlled benchmark conditions stated in the source. | occurred | Sources: · Download data: [JSON](https://newsverum.com/api/v1/articles/mbzuai-faceguardian-image-identity-protection-2026/data/faceguardian-experiment-results?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/mbzuai-faceguardian-image-identity-protection-2026/data/faceguardian-experiment-results?lang=en&format=csv) ## Sources - [Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)]() (Source checked: 2026-10-20; Published: 2026-10-02) --- Cite the canonical URL above. [Editorial standards and corrections](https://newsverum.com/en/editorial)