INSTITUTIONAL DIGITAL REPOSITORY

A novel privacy protection approach with better human imperceptibility

Show simple item record

dc.contributor.author Rana, K
dc.contributor.author Pandey, A
dc.contributor.author Goyal, P
dc.contributor.author Singh, G
dc.contributor.author Goyal, P
dc.date.accessioned 2024-05-26T08:49:56Z
dc.date.available 2024-05-26T08:49:56Z
dc.date.issued 2024-05-26
dc.identifier.uri http://dspace.iitrpr.ac.in:8080/xmlui/handle/123456789/4555
dc.description.abstract Abstract: Our generation is quite obsessed with technology and we like to share our personal information such as photos and videos on the internet via different social networking websites i.e. Facebook, Snapchat, Instagram, etc. Therefore, it becomes easier for others to breach our privacy and harm us in a direct or indirect way. Now, computerized systems have advanced due to the improvements in Machine Learning (ML) algorithms and Artificial Intelligence (AI). These algorithms can extract sensitive information such as face attributes, text information, etc. from images or videos and can be used for privacy breaching. In this paper, we propose a novel privacy protection method by adding intelligent noise to the image while preserving image aesthetics and attributes. We determine multiple attributes for an image such as baldness, smiling, gender, etc. and we intelligently add noise to particular regions of the image that define a particular attribute using the visual explanation technique i.e. GradCam++, thereby preserving the other attributes. The addition of noise is based on the idea of Fast Gradient Sign Method (FGSM) that maximizes the gradients of the loss of an input image to create a new adversarial image. We integrate FGSM adversarial image and GradCam++ output to affect particular attributes only and hence keeping the image human imperceptible. The experiment results show that our attack outperforms the existing attacks including naive FGSM, Projected Gradient Descent (PGD), Momentum Iterative Method (MIM), Shadow Attack (SA), and Fast Minimum Norm (FMN) in terms of preserving attributes and image visual quality, when evaluated on CelebA dataset. en_US
dc.language.iso en_US en_US
dc.subject Adversarial perturbation en_US
dc.subject Visual explanation techniques en_US
dc.subject Social media en_US
dc.subject Convolutional neural networks en_US
dc.title A novel privacy protection approach with better human imperceptibility en_US
dc.type Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account