Learning to Generate Cross-Task Unexploitable Examples
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911319827939328 |
|---|---|
| author | Qu, Haoxuan Xiang, Qiuchi Cai, Yujun Wu, Yirui Mirmehdi, Majid Rahmani, Hossein Liu, Jun |
| author_facet | Qu, Haoxuan Xiang, Qiuchi Cai, Yujun Wu, Yirui Mirmehdi, Majid Rahmani, Hossein Liu, Jun |
| contents | Unexploitable example generation aims to transform personal images into their unexploitable (unlearnable) versions before they are uploaded online, thereby preventing unauthorized exploitation of online personal images. Recently, this task has garnered significant research attention due to its critical relevance to personal data privacy. Yet, despite recent progress, existing methods for this task can still suffer from limited practical applicability, as they can fail to generate examples that are broadly unexploitable across different real-world computer vision tasks. To deal with this problem, in this work, we propose a novel Meta Cross-Task Unexploitable Example Generation (MCT-UEG) framework. At the core of our framework, to optimize the unexploitable example generator for effectively producing broadly unexploitable examples, we design a flat-minima-oriented meta training and testing scheme. Extensive experiments show the efficacy of our framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_13416 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning to Generate Cross-Task Unexploitable Examples Qu, Haoxuan Xiang, Qiuchi Cai, Yujun Wu, Yirui Mirmehdi, Majid Rahmani, Hossein Liu, Jun Computer Vision and Pattern Recognition Unexploitable example generation aims to transform personal images into their unexploitable (unlearnable) versions before they are uploaded online, thereby preventing unauthorized exploitation of online personal images. Recently, this task has garnered significant research attention due to its critical relevance to personal data privacy. Yet, despite recent progress, existing methods for this task can still suffer from limited practical applicability, as they can fail to generate examples that are broadly unexploitable across different real-world computer vision tasks. To deal with this problem, in this work, we propose a novel Meta Cross-Task Unexploitable Example Generation (MCT-UEG) framework. At the core of our framework, to optimize the unexploitable example generator for effectively producing broadly unexploitable examples, we design a flat-minima-oriented meta training and testing scheme. Extensive experiments show the efficacy of our framework. |
| title | Learning to Generate Cross-Task Unexploitable Examples |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.13416 |