TarPro: Targeted Protection against Malicious Image Editing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909541007884288 |
|---|---|
| author | Shen, Kaixin Quan, Ruijie Miao, Jiaxu Xiao, Jun Yang, Yi |
| author_facet | Shen, Kaixin Quan, Ruijie Miao, Jiaxu Xiao, Jun Yang, Yi |
| contents | The rapid advancement of image editing techniques has raised concerns about their misuse for generating Not-Safe-for-Work (NSFW) content. This necessitates a targeted protection mechanism that blocks malicious edits while preserving normal editability. However, existing protection methods fail to achieve this balance, as they indiscriminately disrupt all edits while still allowing some harmful content to be generated. To address this, we propose TarPro, a targeted protection framework that prevents malicious edits while maintaining benign modifications. TarPro achieves this through a semantic-aware constraint that only disrupts malicious content and a lightweight perturbation generator that produces a more stable, imperceptible, and robust perturbation for image protection. Extensive experiments demonstrate that TarPro surpasses existing methods, achieving a high protection efficacy while ensuring minimal impact on normal edits. Our results highlight TarPro as a practical solution for secure and controlled image editing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13994 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TarPro: Targeted Protection against Malicious Image Editing Shen, Kaixin Quan, Ruijie Miao, Jiaxu Xiao, Jun Yang, Yi Cryptography and Security Computer Vision and Pattern Recognition The rapid advancement of image editing techniques has raised concerns about their misuse for generating Not-Safe-for-Work (NSFW) content. This necessitates a targeted protection mechanism that blocks malicious edits while preserving normal editability. However, existing protection methods fail to achieve this balance, as they indiscriminately disrupt all edits while still allowing some harmful content to be generated. To address this, we propose TarPro, a targeted protection framework that prevents malicious edits while maintaining benign modifications. TarPro achieves this through a semantic-aware constraint that only disrupts malicious content and a lightweight perturbation generator that produces a more stable, imperceptible, and robust perturbation for image protection. Extensive experiments demonstrate that TarPro surpasses existing methods, achieving a high protection efficacy while ensuring minimal impact on normal edits. Our results highlight TarPro as a practical solution for secure and controlled image editing. |
| title | TarPro: Targeted Protection against Malicious Image Editing |
| topic | Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.13994 |