The researchers describe the work as evidence that frequency-domain information can complement conventional spatial features, although their analysis identifies important limitations in cross-dataset generalization and baseline comparisons. Modern image generators and editing tools can produce forgeries whose visible imperfections are subtle or absent, making it increasingly difficult to distinguish synthetic material from authentic photographs. Existing detectors often concentrate on spatial cues such as inconsistent textures, illumination, edges and object boundaries.

Those signals can be effective, but they may not transfer well when a detector encounters a generator or manipulation process that it did not encounter during training. The new study focuses on frequency-domain anomalies, patterns that can be difficult to see in the image itself but become accessible after converting feature maps into their spectral representation. MSFEN is built on a pretrained ConvNeXt-Tiny encoder with four stages.

A Fourier Enhancement Module is placed after each stage, giving the network access to both spatial and frequency-domain information at several levels of abstraction. For an input feature map, the module applies a real fast Fourier transform, separates the real and imaginary components of the resulting spectrum, and concatenates them along the channel dimension. A learnable 1-by-1 grouped convolution then modulates the two components independently.

The transformed representation is reconstructed as a complex signal and returned to the spatial domain with an inverse real fast Fourier transform, preserving the original height and width. The module does not stop at the inverse transform. Its output passes through depthwise convolution, a GELU activation and a channel-mixing sequence that expands the number of channels fourfold before compressing them again.

A residual connection combines this result with the original feature map. In this way, the module can amplify potentially informative spectral patterns while retaining the local spatial information carried by the original representation. The design treats frequency and space as complementary rather than competing views of an image: high-frequency components are associated with fine detail and texture, while lower-frequency components provide broader structural information.

Because manipulated regions can range from a small edited object to an entirely synthetic image, MSFEN combines representations from all four ConvNeXt stages. Its Multi-Scale Feature Fusion Module uses 1-by-1 convolutions to align channel dimensions, upsamples the feature maps to a common resolution and concatenates them. Two 3-by-3 convolutional layers then produce a unified representation containing both local texture evidence and higher-level semantic context.

An analysis using one to four backbone stages found that average detection accuracy improved as more scales were incorporated, although the gains began to saturate at four stages. The authors suggest that a three-stage configuration could offer a better balance between accuracy and computational cost in resource-constrained deployments. The fused features feed two related outputs.

One head classifies the entire image as authentic or forged, combining pooled statistical features with a flattened spatial representation. A second head generates a pixel-level forgery mask by convolving and upsampling the fused map to the input resolution. The final training objective combines binary cross-entropy losses for image classification, pixel localization and auxiliary image-level predictions attached to each of the four encoder stages.

These learnable loss weights all began at 1.0 and converged after 100,000 training steps to a ratio of approximately 1:1.07:0.92, indicating that the three objectives contributed at similar levels during optimization. For training and evaluation, the researchers used more than 5,000 forged images from CASIAv2, which includes splicing and copy-move manipulations, and generated 10,000 synthetic images each with ADM and BigGAN. The test sets consisted of the edited-image datasets CASIAv1, Columbia and NIST16, together with 3,000 generated images from ADM, BigGAN and VQDM.

CASIAv2 served as the image-editing dataset used in the experimental setup, whereas the reported editing-benchmark results came from CASIAv1, Columbia and NIST16. The model was trained for 100 epochs on two NVIDIA RTX 3090 graphics processors, using 512-by-512 inputs, AdamW, cosine annealing and a batch size of eight. Baseline models were retrained with the same data split, preprocessing, augmentation and optimization protocol as MSFEN.

Image-level and pixel-level outputs were thresholded at 0.5. The comparison included F3Net, MVSS, PSCC, TruFor, Mesorch and NFA-ViT. The experimental design therefore measured performance under a common training and evaluation setup, although the methods retained their original architectural differences.

The study also supplied pixel-level supervision: public editing datasets used their provided binary masks, fully synthetic images received masks containing all ones, and authentic images received masks containing all zeros. On the unseen VQDM dataset, MSFEN achieved an F1 score of 0.571, accuracy of 0.625 and area under the receiver operating characteristic curve of 0.848. The next-best reported AUC was 0.641 for NFA-ViT, illustrating that performance fell sharply for every tested method when the generative source changed.

The authors characterize the result as preliminary evidence of cross-generator generalization rather than proof that the system is robust to all new generators. On the editing benchmarks, MSFEN achieved the best reported accuracy on NIST16, at 0.634, while Mesorch performed slightly better on CASIAv1. The relatively low absolute performance on NIST16 shows that regional editing remained more difficult than recognition of fully synthetic images.

Stress tests applied Gaussian blur, Gaussian noise and JPEG compression to ADM-generated images. The network reported average accuracies of 0.967 under Gaussian blur, 0.993 under Gaussian noise and 0.993 under JPEG compression, the highest averages among the compared systems for each perturbation. Under particularly strong blur with a kernel size of 23, its accuracy remained 0.914.

The authors caution that these comparatively stable results partly reflect the nature of the test set: generative traces are distributed throughout the image rather than concentrated in a small edited region. At 512-by-512 resolution with a batch size of one, MSFEN contained 46.9 million parameters, required 121.7 billion floating-point operations and ran at 33 frames per second. It used about 45% fewer parameters than Mesorch at comparable FLOPs.

Several qualifications limit how broadly the findings can be interpreted. The baseline systems originated with different backbone architectures, and the proposed Fourier and fusion modules were integrated into a strong ConvNeXt backbone, so the observed gains cannot be completely separated from the benefits of that architecture. Failure cases on NIST16 showed that MSFEN can suppress background responses more effectively than several baselines, yet it still misses highly subtle edits or mistakes natural high-contrast textures for manipulation.

The authors identify broader cross-domain testing, emerging diffusion models and temporal analysis for video as future directions rather than demonstrated capabilities of the present system. Overall, the results support the approach as a promising computational trade-off, while leaving open how it will perform against future generators and more difficult forms of localized manipulation.

Subject of Research: A multi-scale Fourier neural network for detecting and localizing edited and AI-generated image forgeries

Article Title: A lightweight multi-scale fourier enhancement network for image forgery detection

Article References: Hou, Y., Miao, Z., Wang, J., Lu, X., Zhang, R., & Li, Y. (2026). A lightweight multi-scale fourier enhancement network for image forgery detection. Cybersecurity, 9(1), Article 244. https://doi.org/10.1186/s42400-026-00681-5

Image Credits: AI Generated

DOI: 10.1186/s42400-026-00681-5

Keywords: image forgery detection, Fourier analysis, multi-scale learning, ConvNeXt, generative AI, digital forensics, synthetic images, robustness, network efficiency, localization, lightweight, multi-scale

The central insight behind the architecture is that two very different kinds of evidence can reveal a forgery. The first is semantic: a spliced photograph often contains objects whose lighting, edges, or textures do not quite agree with their surroundings, and modern deep learning models have become remarkably good at picking up such visual inconsistencies. The second is statistical: when a digital image is saved as a JPEG file, the compression process leaves a characteristic pattern of errors that changes wherever a region has been pasted in, retouched, or re-saved. Error Level Analysis, or ELA, is a classic forensic technique that amplifies these discrepancies by measuring how much a picture degrades when it is recompressed at a known quality level. Regions that were manipulated after the original compression tend to show different error levels than untouched areas, making them glow under analysis.

ELA has long been valued by forensic practitioners for exactly this reason, but it comes with a practical drawback: computing it across large collections of images is computationally expensive, and interpreting its output by hand or with shallow classifiers is unreliable. The new study sidesteps this bottleneck by vectorizing the ELA computation so that it can run efficiently alongside the RGB stream, turning a slow manual step into a fast, parallelized preprocessing operation that feeds directly into the network. Rather than choosing between appearance and compression evidence, the authors treat both as first-class inputs, processing them in parallel from the very first layer of the model.

Concretely, the architecture consists of two lightweight encoder networks, one receiving the original RGB image and the other receiving its ELA map. Each encoder progressively extracts features at multiple scales, learning representations that capture both local texture anomalies and broader structural context. The two feature streams are then fused and passed into a single shared decoder, which reconstructs a pixel-level map indicating which regions of the image are likely to have been manipulated. Skip connections run from both encoders into the decoder, a design borrowed from the celebrated U-Net segmentation architecture, which preserves fine spatial detail that would otherwise be lost as features pass through successive downsampling stages. This matters enormously in forgery localization, where the difference between a useful forensic tool and a useless one often comes down to whether the output mask aligns precisely with the tampered pixels.

A second key ingredient is attention. The convolution blocks in both the encoder and decoder modules are augmented with the Convolutional Block Attention Module, or CBAM, a widely used mechanism that refines features along two complementary dimensions. The channel attention component learns which feature maps are most informative for distinguishing authentic content from manipulated content, effectively letting the network emphasize, say, the channels that respond to compression artifacts while suppressing those that encode irrelevant background detail. The spatial attention component then highlights the specific pixel locations where suspicious evidence is concentrated. Stacked together, these attention operations sharpen the discriminative power of the learned features without adding substantial computational cost, which is essential for a model intended to be practical rather than merely accurate on a benchmark.

The design choices reflect a deliberate focus on a particular family of forgeries: those that introduce compression inconsistencies. Image splicing, in which a fragment of one photograph is pasted into another, and retouching, in which parts of an image are altered or enhanced, both tend to disturb the uniform JPEG error signature of an authentic file. Because the pasted region typically originates from an image with a different compression history, its error level profile differs from that of its new surroundings. By feeding the ELA map directly into a dedicated encoder, the network can learn to exploit these discrepancies automatically, rather than relying on hand-crafted thresholds that break down when image quality, resolution, or compression settings vary.

This approach distinguishes the work from many recent deep learning methods for forgery detection, which have grown increasingly heavy. Survey literature in the field notes that while numerous proposed models achieve impressive results on standard benchmarks, many are either computationally intensive or generalize poorly to datasets they were not trained on. The authors position their model as a lighter alternative: by using lightweight encoders and an efficient vectorized ELA pipeline, the system aims to deliver competitive localization performance without the enormous parameter counts and inference costs of large vision transformers or heavily engineered multi-stage pipelines. In forensic practice, where investigators may need to triage thousands of images, that efficiency is not a luxury but a requirement.

The evaluation strategy follows the conventions of the field, drawing on established benchmark datasets for manipulated images, including collections such as CASIA, CoMoFoD, and related corpora that have become standard proving grounds for splicing and copy-move detection methods. The reported results show competitive performance on these benchmarks, indicating that the dual-stream design with CBAM-augmented blocks can hold its own against existing approaches while remaining computationally lean. The authors also tested the model on a large collection of real and fake faces hosted publicly on Kaggle, extending the evaluation beyond generic object scenes to the portrait imagery that dominates online misinformation.

Perhaps the most scientifically honest part of the study is what it admits. In cross-dataset evaluation—training on some datasets and testing on a completely unseen one—the model, like most of its predecessors, struggled to generalize to the full diversity of real-world manipulations. This is a well-documented weakness across the entire field of image forensics: models tend to learn dataset-specific cues, such as the compression settings or camera characteristics of a particular corpus, rather than universally valid traces of tampering. When those cues shift, performance drops. The authors explicitly flag this as an important avenue for future research, a candid acknowledgment that benchmark success does not yet translate into forensic reliability in the wild, where adversaries can re-encode, resize, and filter images precisely to erase the very artifacts detectors rely on.

The stakes for this line of research could hardly be higher. Generative tools now allow anyone to fabricate convincing photographs in seconds, and manipulated images have been documented influencing elections, financial markets, and public health debates. Passive forensic techniques—those that detect tampering without access to the original file or cryptographic signatures—are among the few remaining checks on this flood of synthetic and doctored content. By showing that a classical forensic signal like ELA can be vectorized, paired with deep visual features, and refined with attention mechanisms inside a compact encoder-decoder network, the study offers a template for building detectors that are simultaneously fast, accurate, and grounded in the physics of image formation. The road to robust, generalizable forensics remains long, but this work demonstrates that the most promising path may lie not in abandoning classical techniques for deep learning, but in teaching them to work together.

Subject of Research: Dual-stream CNN with RGB–ELA inputs and CBAM attention for detecting and localizing image forgeries

Article Title: An optimized dual-stream CNN with vectorized RGB–ELA inputs and CBAM attention for image forgery detection

Article References: Jaiswal, A. K., Nizami, A., & Srivastava, R. (2026). An optimized dual-stream CNN with vectorized RGB–ELA inputs and CBAM attention for image forgery detection. Neural Computing and Applications, 38(19), Article 796. https://doi.org/10.1007/s00521-026-12534-w

Image Credits: AI Generated

DOI: 10.1007/s00521-026-12534-w

Keywords: image forgery detection, digital image forensics, error level analysis, convolutional neural network, CBAM attention, feature fusion, image splicing, forgery localization, deep learning, U-Net, JPEG compression artifacts, computer vision

The problem the researchers set out to address is one of the most pressing in modern digital media. Forged images are now a critical issue in the transmission of multimedia information, and detection strategies have traditionally split into two broad families. Statistical pixel-based models look for mathematical fingerprints left by editing operations, such as anomalies in compression artifacts, sensor noise patterns, or resampling traces. Physics-based strategies, by contrast, depend on physical indications like illumination direction, shading, reflection, and shadows. The second family has a powerful advantage: a forger can remove statistical traces with enough care, but it is far harder to fabricate a shadow geometry that is fully consistent with the lighting of a scene the object never actually occupied.

Yet physics-based methods have carried a well-known weakness. Standard gradient-based illumination assessment, which estimates the direction of light from the shading gradients on object surfaces, runs into serious limitations and challenges once shadows are present in the image. The difficulty becomes especially severe when objects cast shadows onto one another. In a cluttered scene, a person’s shadow may fall across a wall, a car, and another person simultaneously, and these overlapping shadows lead gradient-based estimators to produce varying or confusing outcomes. The illumination directions inferred from different objects can appear inconsistent even in a completely genuine photograph, generating false alarms that undermine the credibility of the entire forensic analysis.

The new technique tackles this failure mode head-on with a geometric construction the authors call wedge-based shadow analysis. The method begins by selecting key shadow points in the image, the salient locations where shadows attach to or extend from the objects that formed them. Angular wedges are then drawn between these shadow points and their probable forming objects. Each wedge is a cone of possible directions in the image plane, capturing the geometric relationship between an object, the shadow it casts, and the position of the light source that must connect them. Because a single light source must lie within every wedge derived from every consistent object-shadow pair in the scene, the wedges collectively constrain where the illumination can be.

The decision rule that follows is elegantly simple. Linear constraints are applied using these wedges, and the presence of an intersection between their standard limits determines the illumination direction. If the wedges all share a common region, the lighting implied by every shadow in the image agrees, and the image is judged consistent with a single physical light source. Consistency across the wedges therefore represents a genuine image, whereas inconsistency, the failure of the wedges to converge on a shared illumination direction, demonstrates a forgery sample. In other words, a spliced object whose shadow was copied from a differently lit scene will generate a wedge that points somewhere no other wedge in the image points, and the intersection test catches the contradiction.

This approach directly addresses the scenario that breaks gradient-based methods. When objects cast shadows onto each other, the wedges provide a way to reason about the collective geometry of the scene rather than relying on local shading estimates that overlapping shadows contaminate. The angular construction tolerates the ambiguity inherent in any single shadow, which spans a range of possible light positions, while exploiting the fact that a forger’s mistakes accumulate across multiple shadows. A genuine scene with many interlocking shadows still yields wedges that overlap; a composite does not, because the attacker would need to re-render every shadow in the image under a single coherent lighting model to pass the test.

The experimental evaluation used the DSO-1 dataset, a publicly available benchmark containing 44 images, both indoor and outdoor, all featuring shadows. The dataset includes both genuine photographs and manipulated ones, making it a standard proving ground for shadow-based forensics. On this benchmark, the wedge-based model achieved a detection accuracy of 58.73 percent for outdoor images and 67.58 percent for indoor images. The indoor advantage is intuitive: interior scenes tend to have more controlled, single-source lighting, which makes the wedge intersections cleaner and the consistency test more discriminating. Outdoor scenes, with diffuse skylight and multiple environmental light contributions, present a harder geometric puzzle.

Perhaps the most striking result concerns a specific and practically important subset of the data. For genuine outdoor images featuring shadows among objects, the scenes where shadows overlap and objects shade one another, the method reached a potential performance of 82 percent. That figure matters because these overlapping-shadow scenes are precisely the cases where the technique was designed to outperform gradient-based illumination assessment, which tends to produce confusing or contradictory estimates under the same conditions. The result suggests that the wedge formulation converts the very complication that defeats earlier methods, mutual shadow casting, into a source of additional geometric constraints that strengthen the authenticity verdict.

The study situates itself within a rich lineage of physics-based forensics research. Earlier work established that inconsistencies in lighting expose digital forgeries, that shading and shadows can be analyzed jointly to detect manipulation, and that reflection inconsistencies offer a complementary signal. Gradient-based illumination description was developed specifically for forgery detection, and other researchers have pursued optimized three-dimensional lighting environment estimation, linear constraints based on shading and shadows, Lambert model analysis with shadows, and shadow consistency checks using color-space features such as HSV. The wedge technique extends this tradition by targeting the multi-object, mutually shadowing scenes that constrained many of its predecessors, and the authors position it as a viable solution for handling the challenges of gradient-based illumination assessment in difficult real-world scenarios.

The broader significance of the work lies in the ongoing arms race between image manipulation and image verification. As generative tools make convincing composites trivially easy to produce, forensic science increasingly depends on cues that are expensive to fake. Shadows are among the most demanding of these cues, because getting them right requires not just artistic skill but a physically accurate understanding of the scene’s lighting geometry. A method that reads the angular relationships between objects and their shadows, and that remains robust when those shadows interlock, adds a meaningful layer of defense. The authors’ findings, drawn from a modest but well-established benchmark, indicate that wedge-based shadow analysis can serve as a practical component in the forensic toolkit, complementing statistical detectors and metadata analysis. For editors, journalists, courts, and platforms confronting a daily flood of questionable imagery, the message is a compelling one: the light in a photograph always tells the truth, and now there is a more reliable way to make the shadows testify.

Subject of Research: Physics-based image forgery detection using wedge-based analysis of object shadows and illumination consistency

Article Title: Illuminating authenticity using deciphering image forgery through scene object shadow analysis

Article References: Surve, D., & Nimkar, A. (2026). Illuminating authenticity using deciphering image forgery through scene object shadow analysis. Multimedia Tools and Applications, 85(10), Article 801. https://doi.org/10.1007/s11042-026-21956-6

Image Credits: AI Generated

DOI: 10.1007/s11042-026-21956-6

Keywords: image forgery detection, shadow analysis, digital forensics, illumination direction, physics-based methods, wedge-based analysis, DSO-1 dataset, photo manipulation, computer vision, image authentication, multimedia security, lighting consistency

The review begins by grounding readers in the two great families of forensic techniques. Active methods embed protective information into an image before it ever leaves the camera or the editing suite. Digital watermarking is the classic example: a fragile watermark is woven into pixel data so that any subsequent alteration disturbs the embedded pattern and reveals the tampering. Watermarking has proven valuable in domains such as medical imaging, where authentication of every pixel is a legal and clinical necessity, and researchers have even developed lossless deep-learning-based watermarking schemes for that purpose. The weakness of active approaches, however, is structural. They require cooperation at the point of capture, and the overwhelming majority of images circulating online carry no such protection.

Passive, or blind, forensics asks the opposite question: what traces does manipulation itself leave behind? Every act of forgery, however careful, disturbs the statistical fabric of an image. Resampling introduces periodic correlations that betray scaling or rotation, a phenomenon first formalized by Popescu and Farid in 2005. JPEG compression leaves ghosts and block-grained artifacts that can be analyzed to localize edits. Camera characteristics such as chromatic aberration, sensor noise patterns, and camera response functions create internal consistency checks, because a spliced-in region often arrives with the fingerprint of a different device. Even the physics of light plays a role: inconsistent shading and shadows across a composite scene can expose a fabrication, an approach pioneered by Farid’s group and later extended into perceptual metrics for detecting retouching.

Within passive forensics, the review devotes particular attention to copy-move forgery, the deceptively simple act of copying a region of an image and pasting it elsewhere to conceal or duplicate content. Because the pasted patch comes from the same image, it inherits the same noise, lighting, and compression history, defeating many classic consistency checks. Early defenses relied on exhaustive block matching, notably Fridrich and colleagues’ 2003 block-based method, and on transform-domain tricks such as combining the discrete cosine transform with singular value decomposition. The field then shifted toward keypoint detectors: SIFT, SURF, ORB, KAZE, and Harris corners each offered distinctive, scale-tolerant descriptors that could be matched across an image to reveal duplicated regions, with clustering schemes such as J-Linkage and mDBSCAN used to separate genuine matches from coincidental ones.

Keypoint methods, however, struggle with small or extremely smooth tampered regions that yield too few distinctive features, and they can be defeated by geometric warping of the copied patch. This is where deep learning entered the picture. Convolutional neural networks learn manipulation traces directly from data, and architectures such as TamperNet, BusterNet, and Noiseprint demonstrated that networks could localize tampered areas, distinguish source from target regions in copy-move forgeries, and even recover camera-model fingerprints. Dual-branch CNNs, coarse-to-refined networks paired with adaptive clustering, and self-consistency learning, in which a network learns that spliced regions fail to cohere with their surroundings, all pushed accuracy upward. The review catalogs these architectures and compares their training regimes and performance across the field’s standard benchmarks: CASIA, MICC, GRIP, and CoMoFoD.

The most distinctive contribution of the survey is its focus on optimization, a layer of the pipeline that often goes unexamined in mainstream coverage. Deep networks are riddled with hyperparameters, from learning rates to layer configurations, and feature-matching pipelines involve thresholds and clustering parameters that are notoriously difficult to set by hand. Metaheuristic algorithms, nature-inspired search procedures such as particle swarm optimization, ant colony optimization, genetic algorithms, the multi-verse optimizer, the Archimedes optimization algorithm, and even more exotic entrants like the political optimizer and battle royale optimization, offer a way to tune these choices automatically. The review documents systems that pair CNNs with a hybrid spotted hyena and grasshopper optimizer, superpixel clustering refined by emperor penguin optimization, and golden ball optimization applied to medical image forensics, among many others.

The payoff for this hybridization is quantifiable. Across the studies surveyed, CNN-plus-optimization frameworks consistently outperform non-hybrid methods, reaching the 98 to 100 percent accuracy band on benchmark datasets. Optimization also improves robustness, helping detectors cope with post-forgery operations such as compression, noise addition, and blurring that would otherwise degrade matching. Yet the authors are candid about the limits. Robustness to geometrical distortions, rotations, scalings, and reflections remains a persistent weak point, since many detectors assume that copied regions appear in near-original form. Computational inefficiency is a second concern: some pipelines demand processing power incompatible with real-time or mobile deployment, a gap that lightweight architectures such as MobileNets and U-Net-style segmentation backbones are only beginning to close. Poor generalization across diverse forgery sources is the third weakness, as models trained on one dataset or manipulation type often falter on another.

Looking forward, the review identifies three research directions that could reshape the field. Transformer-based architectures, following the ViT and Swin Transformer lineage, are already being adapted for forgery localization, with recent work on multi-exit vision transformers suggesting gains in both robustness and efficiency. GAN-based detection is a double-edged frontier: generative adversarial networks can both synthesize deepfakes and be trained to recognize the artificial fingerprints that generators inadvertently leave behind, a question explored since researchers first asked whether GANs leave detectable traces. And real-time forensic systems, capable of operating across varied imaging conditions on everything from smartphones to newsroom verification desks, represent the practical destination toward which much of this research is pointing. Semi-supervised localization methods and meta-learning approaches that let models adapt quickly to new manipulation types also feature among the promising avenues.

What makes this survey timely is the asymmetry it highlights between the tools of deception and the tools of detection. Generative models improve at a pace set by commercial competition, while forensic systems must generalize to manipulations they have never seen, often under compression and resizing imposed by social media platforms. The authors’ synthesis suggests that neither raw deep learning nor clever optimization alone will win that race; it is the disciplined combination of the two, with metaheuristic search tuning learned models and learned models supplying the representational power that handcrafted features lack, that currently defines the state of the art. For journalists, courts, and platforms that increasingly depend on image provenance, the message is both reassuring and cautionary: near-perfect detection is now achievable in the laboratory, but translating that performance into robust, fast, universally trustworthy verification remains the field’s unfinished work.

Subject of Research: Image forgery detection using deep learning frameworks and metaheuristic optimization techniques

Article Title: Advancing image forgery detection: An investigation into optimization techniques and deep learning frameworks

Article References: R, A. M., J, D., & Kulkarni, R. N. (2026). Advancing image forgery detection: An investigation into optimization techniques and deep learning frameworks. Multimedia Tools and Applications, 85(9), Article 746. https://doi.org/10.1007/s11042-026-21916-0

Image Credits: AI Generated

DOI: 10.1007/s11042-026-21916-0

Keywords: image forgery detection, copy-move forgery, deep learning, CNN, metaheuristic optimization, particle swarm optimization, digital forensics, transformers, GAN, deepfake detection, CASIA dataset, benchmark datasets