Jul 2026· International Journal of Innovative Research in Science Engineering and Technology· Vol 15· 0 citations
TL;DR
An in-depth survey of fifteen state-of-art methodologies including classical CNN models, temporal-spatial video recognition, transformer-based networks, explainable AI (XAI) models, and models that combine multimodal large language model (LLM) products are provided.
Abstract
With the progress of generative adversarial networks (GANs), diffusion models, and large-scale deep
learning models, deepfake technology has developed rather quickly and becomes a significant challenge to digital
integrity, cybersecurity, journalism, and forensic investigations. While conventional CNN-based deepfake detectors
demonstrated high accuracy in detecting visual artifacts; it only fulfills the lack of robustness as well as cross domain
generalization and interpretability. The review provides an in-depth survey of fifteen state-of-art methodologies
including classical CNN models, temporal-spatial video recognition, transformer-based networks, explainable AI (XAI)
models, and models that combine multimodal large language model (LLM) products. The taxonomy classifies the
current techniques in terms of representational features, learning models, interpretability procedures and deployment
capability. Particular attention is paid to explainable and human-friendly AI systems including Grad-CAM
visualizations, captioning systems, and narrative generation modules. Some of the important issues include adversarial
robustness, bias in the data sets, computational complexity, cross-dataset generalization, and computational limitations
in the real world. Lastly, the release of new research directions in terms of creating reliable, scalable, and
understandable deepfake detectors is described.
Deepfakes pose growing risks to information integrity, yet many detectors perform well only on the datasets they were trained on and remain opaque to human analysts. A robust, explainable detection framework is presented that combines a CNN backbone for extracting spatial artifacts with an LSTM module for modeling temporal inconsistencies across frames. To make decisions auditable, the architecture incorporates Grad-CAM for spatial heatmaps, SHAP for quantitative feature attribution, and LIME for local surrogate explanations. The system was trained primarily on FaceForensics++ with stratified sampling and augmentation to reduce dataset bias and evaluated on multiple external benchmarks to assess cross-domain generalization. Experimental results show strong detection metrics, such as accuracy of 96.3%, precision of 95.8%, recall of 96.7%, and an F1-score of 96.2%, along with robust performance under JPEG compression, Gaussian noise, and FGSM adversarial attacks. By coupling high detection accuracy with transparent explanations, the proposed approach enhances forensic decision support and increases practical readiness for content verification systems.
Lastone Banda, Esther J.· International Journal of Dat...· 0 citations
The development of deepfakes is becoming a serious threat to multimedia security, therefore making the need for robust and efficient detection systems vital. In this paper, an in-depth review of deep learning approaches that have been developed towards the automatic detection of deepfake videos is carried out. This includes twenty research papers published within the period of 2023 to 2026, discussing deep fake video detectors that use Convolutional Neural Networks (CNN) models, transformer models, graph models, ensemble learning models, and hybrids. Spatial and temporal learning approaches adopted in the detection of facially manipulated videos are discussed. Nonetheless, despite numerous developments, current detection systems are facing challenges like computational complexity, poor generalization, and susceptibility to distortions, among others. Also, the use of a large annotated database further restricts the application. Some of the advancements made recently include vision transformers, graph neural networks, and optimization of ensemble models to enhance performance. The future research needs to concentrate more on lightweight and generalized deep learning models that can be scalable and interpretable. The paper offers a systematic review of recent advancements in deepfake video detection research.
M. Nirmala, P. Gowr· 2026 International Conferenc...· 0 citations
Rapid advances in deep learning technology have led to the emergence of artificial intelligence (AI) media that is very similar to reality, called deepfakes, which have the potential to pose a serious threat to information integrity and public trust. Although detection methods using Convolutional Neural Networks (CNN) have been developed, most still struggle with generalization, particularly in distinguishing modern deepfakes from non-standard original images such as selfies, which often leads to high false positive rates. This study introduces a robust detection model based on the EfficientNetB0 architecture implemented through transfer learning techniques. To improve generalization capabilities and minimize bias, we compiled a large and balanced combined dataset by combining three different public datasets (including classic deepfakes, face swaps, and many authentic selfies). The model was trained using a two-stage strategy: first for feature extraction, then refinement with a very low learning rate. The model's performance was thoroughly evaluated on stratified test data using five key metrics. The results of the experiment showed outstanding performance, achieving 99.81% accuracy and a Macro F1 score of 99.81%. Additionally, the reliability metrics ROC-AUC, Average Precision (AP), and True Positive Rate (TPR) all reached 99.99%, while the False Positive Rate (FPR) remained strictly at 1%. As proof of concept, this optimized model was implemented in a web prototype built using the Django framework, allowing users to upload images and receive classification results in real-time.
Muhammad Erico Revaldo, Burhanudin Rabbani, Wildan Humaidi et al.· Jurnal Teknoinfo· 0 citations
Text-to-image generation is an increasingly fast-paced field of generative artificial intelligence, consisting of synthesizing images of high quality and semantic consistency based on natural language descriptions. In this paper, we give an extensive overview of the approach to text-to-image generation using deep learning, including the most common core model families, architecture designs, training approaches, and evaluation systems. We discuss the paradigms of the generative adversarial networks (GANs), variational autoencoders (VAEs), transformer-based designs, and diffusion models, with the last one representing the state of the art in image generation models. The review also discusses key aspects of pipelines such as text encoding, cross-modal alignment, mechanisms of attention, and decoding images. Popular datasets, methods, and metrics of evaluation, including Fréchet Inception Distance (FID) and CLIP-based similarity, are discussed. The application domains that involve creative content creation, medical imaging, education and industrial design are critically discussed. Despite significant advances, various issues still exist, such as low stability in training, excessive computational complexity, amplification of bias, generated images, and text–image alignment errors. Moral and social issues, such as misinformation, intellectual property, and equity, are critically examined. Lastly, we present future research directions to more controllable, more efficient and more interpretable text-to-image systems, focusing on multimodal foundation models and human–AI collaborative design.
The rapid advancement of artificial intelligence (AI) has significantly changed the way digital visual content is created,
enabling the generation of highly realistic synthetic images and videos. While these technologies support many beneficial
applications, they have also facilitated the creation of manipulated visual content, commonly known as deepfakes, which pose
serious challenges to information authenticity, public trust, cybersecurity, and digital forensic investigations. As image
manipulation techniques continue to evolve through advanced models such as Generative Adversarial Networks (GANs) and
diffusion-based frameworks, conventional detection methods relying on handcrafted features have become increasingly
inadequate. In response, deep learning approaches integrated with transfer learning have emerged as effective solutions due to
their ability to leverage pre-trained models for extracting robust and discriminative features, even when limited training data are
available. This review presents a comprehensive analysis of recent deep learning and transfer learning techniques for fake
image detection. It examines widely adopted convolutional neural network (CNN) architectures, benchmark datasets, evaluation
metrics, and current research developments. Furthermore, the paper provides a comparative assessment of existing methods by
highlighting their strengths, limitations, and performance characteristics. Finally, it identifies major research challenges and
outlines future directions for developing robust, scalable, and generalizable fake image detection systems capable of addressing
the growing threats posed by AI-generated visual content in cyberspace
Nisha Parveen, Anjali Saxena· International Journal for Re...· 0 citations
Deep fake technology has emerged as a pressing global issue, enabling the creation of highly realistic fake videos with severe implications for misinformation, privacy breachesand digital security. The widespread misuse of deep fakes in areas like political propaganda, financial fraud and personal defamation underscores the urgent need for effective detection mechanisms. This paper proposes an Illusion Interception Tool, a robust deep fake detection system, as a novel approach towards the deception of Deep Fake Videos. Though we have some existing solutions for the same, they often focus solely on spatial or temporal inconsistencies and limit their effectiveness against sophisticated forgeries. This paper addresses these gaps with a hybrid framework that combines ResNeXt convolutional neural networks (CNNs) for detailed spatial analysis and long short-term memory (LSTM) networks for capturing temporal dynamics with soft attention. This novel approach effectively identifies both pixel-level artifacts and frame-wise inconsistencies by achieving significant improvements in accuracy and robustness. Thus, by evaluating benchmark datasets such as Face Forensics++ and Celeb-DF here, the present method outperforms existing techniques and achieves up to 94.8% accuracy. Ablation studies confirm the complementary nature of spatial and temporal analysis and our method generalizes well to unseen data.