Fant\^omas: Understanding Face Anonymization Reversibility

arXiv:2210.10651v3 Announce Type: replace-cross
Abstract: Face images are a rich source of information that can be used to identify individuals and infer private information about them. To mitigate this privacy risk, anonymizations employ transformations on clear images to obfuscate sensitive information, all while retaining some utility. Albeit published with impressive claims, they sometimes are not evaluated with convincing methodology.
Reversing anonymized images to resemble their real input -- and even be identified by face recognition approaches -- represents the strongest …

abstract anonymization arxiv clear cs.cr cs.lg face identify images information privacy risk them type understanding utility while