Abstract
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.
Originalsprache | Englisch |
---|---|
Titel | DF-Net: The Digital Forensics Network for Image Forgery Detection |
Redakteure/-innen | Peter Corcoran |
Erscheinungsort | https://iprcs.github.io/pdf/IMVIP2023_Proceeding.pdf |
Seiten | 120-127 |
Seitenumfang | 8 |
Publikationsstatus | Veröffentlicht - 2023 |
Veranstaltung | 25th Irish Machine Vision and Image Processing Conference - Galway, Ireland, Galway, Irland Dauer: 30 Aug. 2023 → 1 Sept. 2023 https://www.universityofgalway.ie/c3i/news-&-events/imvip_2023/ |
Konferenz
Konferenz | 25th Irish Machine Vision and Image Processing Conference |
---|---|
Kurztitel | IMVIP 2023 |
Land/Gebiet | Irland |
Stadt | Galway |
Zeitraum | 30/08/23 → 1/09/23 |
Internetadresse |
Research Field
- Computer Vision