DF-Net: The Digital Forensics Network for Image Forgery Detection
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_ | 1866916664919982080 |
|---|---|
| author | Fischinger, David Boyer, Martin |
| author_facet | Fischinger, David Boyer, Martin |
| contents | The orchestrated manipulation of public opinion, particularly through manipulated images, often spread via online social networks (OSN), has become a serious threat to society. In this paper we introduce the Digital Forensics Net (DF-Net), a deep neural network for pixel-wise image forgery detection. The released model outperforms several state-of-the-art methods on four established benchmark datasets. Most notably, DF-Net's detection is robust against lossy image operations (e.g resizing, compression) as they are automatically performed by social networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22398 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DF-Net: The Digital Forensics Network for Image Forgery Detection Fischinger, David Boyer, Martin Computer Vision and Pattern Recognition The orchestrated manipulation of public opinion, particularly through manipulated images, often spread via online social networks (OSN), has become a serious threat to society. In this paper we introduce the Digital Forensics Net (DF-Net), a deep neural network for pixel-wise image forgery detection. The released model outperforms several state-of-the-art methods on four established benchmark datasets. Most notably, DF-Net's detection is robust against lossy image operations (e.g resizing, compression) as they are automatically performed by social networks. |
| title | DF-Net: The Digital Forensics Network for Image Forgery Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.22398 |