As the popularity of ML models continues to increase, concerns about the risks associated with black box models have become more prominent. While much attention has been given to the development of unfair models, another concern is often overlooked: the privacy risks posed by ML models.
Join me in this talk, where I will explain the privacy risks inherent in Machine Learning models. Beyond exploring potential attacks, I will explain how techniques like Differential Privacy and tools like Opacus (https://github.com/pytorch/opacus) can be crucial in training more robust and secure models.