DF-Net: The Digital Forensics Network for Image Forgery Detection

David Fischinger; Martin Boyer

DF-Net: The Digital Forensics Network for Image Forgery Detection

David Fischinger (Author and Speaker), Martin Boyer

Data Science & Artifical Intelligence

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

61 Downloads (Pure)

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.

Original language	English
Title of host publication	DF-Net: The Digital Forensics Network for Image Forgery Detection
Editors	Peter Corcoran
Place of Publication	https://iprcs.github.io/pdf/IMVIP2023_Proceeding.pdf
Pages	120-127
Number of pages	8
Publication status	Published - 2023
Event	25th Irish Machine Vision and Image Processing Conference - Galway, Ireland, Galway, Ireland Duration: 30 Aug 2023 → 1 Sept 2023 https://www.universityofgalway.ie/c3i/news-&-events/imvip_2023/

Conference

Conference	25th Irish Machine Vision and Image Processing Conference
Abbreviated title	IMVIP 2023
Country/Territory	Ireland
City	Galway
Period	30/08/23 → 1/09/23
Internet address	https://www.universityofgalway.ie/c3i/news-&-events/imvip_2023/

Research Field

Computer Vision

Keywords

Computer Vision
Image Forgery Detection
Manipulation Detection

Access to Document

IMVIP_2023-ID22_DFNet_final_submissionSubmitted manuscript, 8.01 MB

Cite this

@inproceedings{660c4f8b7d8a4ec7b348e5f4a241954f,

title = "DF-Net: The Digital Forensics Network for Image Forgery Detection",

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{\textquoteright}s detection is robust against lossy image operations (e.g resizing, compression) as they are automatically performed by social networks.",

keywords = "Computer Vision, Image Forgery Detection, Manipulation Detection",

author = "David Fischinger and Martin Boyer",

year = "2023",

language = "English",

isbn = "978-0-9934207-8-8 ",

pages = "120--127",

editor = "Corcoran, {Peter }",

booktitle = "DF-Net: The Digital Forensics Network for Image Forgery Detection",

note = "25th Irish Machine Vision and Image Processing Conference, IMVIP 2023 ; Conference date: 30-08-2023 Through 01-09-2023",

url = "https://www.universityofgalway.ie/c3i/news-&-events/imvip_2023/",

}

DF-Net: The Digital Forensics Network for Image Forgery Detection. / Fischinger, David (Author and Speaker); Boyer, Martin.
DF-Net: The Digital Forensics Network for Image Forgery Detection. ed. / Peter Corcoran. https://iprcs.github.io/pdf/IMVIP2023_Proceeding.pdf, 2023. p. 120-127.

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

TY - GEN

T1 - DF-Net: The Digital Forensics Network for Image Forgery Detection

AU - Boyer, Martin

A2 - Fischinger, David

A2 - Corcoran, Peter

PY - 2023

Y1 - 2023

N2 - 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.

AB - 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.

KW - Computer Vision

KW - Image Forgery Detection

KW - Manipulation Detection

UR - https://iprcs.github.io/pdf/IMVIP2023_Proceeding.pdf

M3 - Conference Proceedings with Oral Presentation

SN - 978-0-9934207-8-8

SP - 120

EP - 127

BT - DF-Net: The Digital Forensics Network for Image Forgery Detection

CY - https://iprcs.github.io/pdf/IMVIP2023_Proceeding.pdf

T2 - 25th Irish Machine Vision and Image Processing Conference

Y2 - 30 August 2023 through 1 September 2023

ER -

DF-Net: The Digital Forensics Network for Image Forgery Detection

Abstract

Conference

Research Field

Keywords

Access to Document

Other files and links

Fingerprint

Cite this