The goal of privacy-preserving (deep) learning is to train a model while preserving privacy of the training dataset. Typically, it is understood that the trained model should be privacy-preserving (e.g., due to the training algorithm being differentially private).
Fawkes is an image cloaking system that helps individuals inoculate their images against unauthorized facial recognition models. Fawkes achieves this by helping users add imperceptible pixel-level changes ("cloaks") to their own photos before releasing them. When used to train facial recognition models, these "cloaked" images produce functional models that consistently cause normal images of the user to be misidentified.
Canvas Method is a method for inference attacks on object detection models. It draws a predicted bounding box distribution on an empty canvas for an attack model input. The canvas is initially set to an image of 300$\times$300 pixels in size, where every pixel has a value of zero and the boxes drawn on the canvas have the same center as the predicted boxes and the same intensity as the prediction scores.