MediaEval 2019: Concealed FGSM Perturbations for Privacy Preservation
This addresses privacy preservation in images for users, but it is incremental as it builds on existing fast gradient sign method techniques.
This work tackled the problem of manipulating images to conceal them from automatic scene classifiers while preserving original quality, achieving results by minimizing damage to image appeal through two perturbation methods.
This work tackles the Pixel Privacy task put forth by MediaEval 2019. Our goal is to manipulate images in a way that conceals them from automatic scene classifiers while preserving the original image quality. We use the fast gradient sign method, which normally has a corrupting influence on image appeal, and devise two methods to minimize the damage. The first approach uses a map of pixel locations that are either salient or flat, and directs perturbations away from them. The second approach subtracts the gradient of an aesthetics evaluation model from the gradient of the attack model to guide the perturbations towards a direction that preserves appeal. We make our code available at: https://git.io/JesXr.