IFDNet: Image forgery detection with Dynamic Contextual Modulation using Deep Learning

2025 · doi:10.22541/au.174291164.43944625/v1
preprint OA: closed
Full text JSON View at publisher
⚙ AI-generated deep summary by claude@2026-06, 2026-06-24 · read from full text ⓘ

This preprint proposes IFDNet, a deep learning image forgery detection network, that uses newly introduced Dynamic Contextual Modulation Blocks (DCMB) to enhance feature extraction and classification of authentic versus manipulated images. The model is evaluated on public image forgery datasets CASIA V2.0 and MICC-F2000, where it reports higher accuracy, precision, and recall than conventional approaches, and attributes gains to improved feature representation for complex forgeries. A stated limitation is that the work is a preprint and has not been peer reviewed, with potentially preliminary data. The paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Abstract

Images are crucial in various domains, including journalism, security, and healthcare, as they convey significant amounts of information. However, with the advancement of digital editing tools and the increasing prevalence of counterfeit images, the need for effective image forgery detection has become more critical than ever. Conventional image forgery detection techniques struggle to keep pace with evolving manipulation methods, often requiring extensive manual intervention and computational resources. This paper proposes Image Forgery Detection Network(IFDNet) architecture for image forgery detection task. The proposed architecture is an effective and efficient Deep Learning (DL) architecture incorporating newly introduced Dynamic Contextual Modulation Block (DCMB) for enhanced feature extraction and classification. The proposed IFDNet model is evaluated on widely used publicly available image forgery datasets like CASIA V2.0, and MICC-F2000 demonstrating its superior performance in differentiating authentic and manipulated images. Experimental results show that the proposed IFDNet model achieves high accuracy, precision, and recall, outperforming conventional approaches. The integration of DCMB significantly improves feature representation, enabling robust detection of complex forgeries. This advanced approach provides an efficient and scalable solution for image forgery detection, making a significant contribution to the field of digital image forensics.
Full text 2,508 characters · extracted from oa-doi-fallback · 2 sections · click to expand

Abstract

Images are crucial in various domains, including journalism, security, and healthcare, as they convey significant amounts of information. However, with the advancement of digital editing tools and the increasing prevalence of counterfeit images, the need for effective image forgery detection has become more critical than ever. Conventional image forgery detection techniques struggle to keep pace with evolving manipulation methods, often requiring extensive manual intervention and computational resources. This paper proposes Image Forgery Detection Network(IFDNet) architecture for image forgery detection task. The proposed architecture is an effective and efficient Deep Learning (DL) architecture incorporating newly introduced Dynamic Contextual Modulation Block (DCMB) for enhanced feature extraction and classification. The proposed IFDNet model is evaluated on widely used publicly available image forgery datasets like CASIA V2.0, and MICC-F2000 demonstrating its superior performance in differentiating authentic and manipulated images. Experimental results show that the proposed IFDNet model achieves high accuracy, precision, and recall, outperforming conventional approaches. The integration of DCMB significantly improves feature representation, enabling robust detection of complex forgeries. This advanced approach provides an efficient and scalable solution for image forgery detection, making a significant contribution to the field of digital image forensics. Supplementary Material File (ifdnet.pdf) - Download - 1.23 MB Information & Authors Information Version history Copyright This work is licensed under a Non Exclusive No Reuse License.

Keywords

Authors Metrics & Citations Metrics Article Usage 234views 110downloads Citations Download citation PUNEETH S, Shyam Lal, B.S. Raghavendra. IFDNet: Image forgery detection with Dynamic Contextual Modulation using Deep Learning. Authorea. 25 March 2025. DOI: https://doi.org/10.22541/au.174291164.43944625/v1 DOI: https://doi.org/10.22541/au.174291164.43944625/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu.

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

⚙ Ask this paper AI returns verbatim quotes from the full text · source: oa-doi-fallback ⓘ

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00