{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/e2e21b5f24c84b6787f11bc94cba0c35\" frameborder=\"0\" width=\"1280\" height=\"960\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":960,"width":1280,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":960,"thumbnail_width":1280,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/e2e21b5f24c84b6787f11bc94cba0c35-00001.gif","duration":268.142,"title":"Zero Knowledge Differential Privacy: Introducing Delta Z 👥🔒","description":"Hi everyone, in this video message, I will be introducing Delta Z, the first implementation of Zero Knowledge differential privacy. I will explain the flaws of pseudo-anonymity and the need for a better paradigm like differential privacy. I will also discuss how Delta Z adds noise to the data while maintaining accuracy and privacy. Additionally, I will demonstrate a univariate Gaussian noise additive mechanism and show how privacy budgets can affect the accuracy of query results. Finally, I will touch upon the potential applications of Delta Z, from crowdsource dynamic databases to trustless training of machine learning models."}