Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913306109804544 |
|---|---|
| author | Perez, Fabian Lopez, Jhon Arguello, Henry |
| author_facet | Perez, Fabian Lopez, Jhon Arguello, Henry |
| contents | In the era of cloud computing and data-driven applications, it is crucial to protect sensitive information to maintain data privacy, ensuring truly reliable systems. As a result, preserving privacy in deep learning systems has become a critical concern. Existing methods for privacy preservation rely on image encryption or perceptual transformation approaches. However, they often suffer from reduced task performance and high computational costs. To address these challenges, we propose a novel Privacy-Preserving framework that uses a set of deformable operators for secure task learning. Our method involves shuffling pixels during the analog-to-digital conversion process to generate visually protected data. Those are then fed into a well-known network enhanced with deformable operators. Using our approach, users can achieve equivalent performance to original images without additional training using a secret key. Moreover, our method enables access control against unauthorized users. Experimental results demonstrate the efficacy of our approach, showcasing its potential in cloud-based scenarios and privacy-sensitive applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_05828 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning Perez, Fabian Lopez, Jhon Arguello, Henry Computer Vision and Pattern Recognition Cryptography and Security Image and Video Processing In the era of cloud computing and data-driven applications, it is crucial to protect sensitive information to maintain data privacy, ensuring truly reliable systems. As a result, preserving privacy in deep learning systems has become a critical concern. Existing methods for privacy preservation rely on image encryption or perceptual transformation approaches. However, they often suffer from reduced task performance and high computational costs. To address these challenges, we propose a novel Privacy-Preserving framework that uses a set of deformable operators for secure task learning. Our method involves shuffling pixels during the analog-to-digital conversion process to generate visually protected data. Those are then fed into a well-known network enhanced with deformable operators. Using our approach, users can achieve equivalent performance to original images without additional training using a secret key. Moreover, our method enables access control against unauthorized users. Experimental results demonstrate the efficacy of our approach, showcasing its potential in cloud-based scenarios and privacy-sensitive applications. |
| title | Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning |
| topic | Computer Vision and Pattern Recognition Cryptography and Security Image and Video Processing |
| url | https://arxiv.org/abs/2404.05828 |