MétaCan
Menu
Back to cohort
Record W4409793555 · doi:10.61091/jcmcc127a-246

Remote Image Tampering Detection Combining Deep Neural Networks

2025· article· en· W4409793555 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

venuePublished in a venue whose home country is Canada.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueJournal of Combinatorial Mathematics and Combinatorial Computing · 2025
Typearticle
Languageen
FieldComputer Science
TopicDigital Media Forensic Detection
Canadian institutionsnot available
Fundersnot available
KeywordsArtificial intelligenceComputer scienceImage (mathematics)Artificial neural networkComputer visionDeep neural networksDeep learningPattern recognition (psychology)

Abstract

fetched live from OpenAlex

In the current information age, image tampering detection technology is crucial to ensure the integrity and authenticity of digital media, and remote image tampering detection technology combined with deep neural networks has become a research hotspot.This paper adopts convolutional neural network as the main detection tool, and on the improved DPN network model, the feature fusion module based on the attention mechanism is used to fuse the two features in this paper.In this way, the image tampering detection technique based on dual-stream feature fusion is proposed in this paper.The precision, recall and F value of the detection algorithm in this paper are better than the comparison algorithm.When the image compression quality factor is reduced to 20, the precision rate, recall rate, and F value of this paper's algorithm do not appear to be greatly reduced, and the reduction is only 0.028, 0.041, and 0.042.This paper's image tampering detection algorithm, which fuses the frequency domain branching module and the attention mechanism feature fusion module, has a higher detection efficiency.And the Accuracy rate, Recall rate and F Value of this paper's algorithm on image level detection are 17.8%, 15.3% and 16.3% higher than that of DCT algorithm respectively.In conclusion, the remote image tampering technique combined with deep neural network provides an effective solution to ensure the authenticity and integrity of images.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.797
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.007
GPT teacher head0.232
Teacher spread0.225 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it